Anthropic's Circuit Tracing and the Utility of Interpretability — Emmanuel Amiesen

Source material

Transcript

[MUSIC PLAYING] All right, we are actually going to record this as an intro to the main episode.

But here we have my trusty co-host, guest host, I guess, Vibhu, as well as Emmanuel from Menthropic.

We are going to talk about the circuit tracing stuff and all the interpretability work.

But Emmanuel, maybe you want to do a quick self-intro because before we get into it.

Yeah, sure.

I'm Emmanuel.

I work on the interpretability team here at Menthropic, more specifically on the circuits team.

So we recently released a pair of papers about the work that we've been doing over the last months.

And even more recently, we released some code in partnership with the Menthropic Fellows program.

It was mostly built by Menthropic Fellows that lets people play with the research, basically.

And so happy to talk about that.

And we also hope to keep releasing more things and partner with other groups that are working on similar stuff.

Yeah, amazing.

We'll get deeper into the behind the scenes on the main podcast.

But let's maybe just dive right in into what you released, because that's the most topical thing.

This is literally just launched it yesterday.

And we'll probably release it in at least this episode in a few days.

So yeah, what can people do?

Or what do you recommend people try?

Totally.

So at a really high level, the idea of the research itself is to try to explain some of the computation that a model did when it predicted a given token.

And so in our paper, we show how to do this.

And then we show examples of us doing this on internal private models.

And then the release this week lets anyone do it for a set of open source models.

So notably, maybe the most easy one here is Gemma 2.2b.

So you can think of some prompt.

And you can explain any token that the model samples.

And explains here means just basically blow up the internal state of the model and show all of the intermediate things that the model was thinking about before it got to the final token that it predicted.

Yeah, so some of the things that you guys put out is in the circuit tracing.

You have a few core examples.

So we can see how these models have internal reasoning states.

And there's multi-cop reasoning.

And some of the stuff that we talked about on the podcast was, how can people that are interested in how models work do anything?

So what are open questions?

How can people contribute?

And it seems like the follow up is, OK, it's been a few weeks.

Here's a huge library.

So I guess before we even get into it, what are some open questions that you would expect people to play around with?

What are people going to do?

Why should we probe Gemma, Blama?

What are interesting things we can do?

And any tips on using it?

Yeah, I think there's maybe two to three categories of things that people could do.

I'll go from the most basic, low effort to, hey, if you want to dedicate a month of your life, you could do that.

The most basic thing is-- so Gemma, too, and Blama want to be like smaller models.

But they can still do a bunch of stuff.

And for most of the things that they can do, we still don't really know or have a good mental model of how it is that they do the things that they do.

So to give you an example, one of the things in the paper is to serve multi-hop reasoning where we ask Cloud 3.55 who are like, oh, the capital of the state where Dallas is Austin.

It turns out that Gemma can do this also.

And so as part of the release, we have a notebook where Michael Hanna, one of the anthropic fellows, walks through a bunch of examples, including this one.

And it's really cool because you can see that actually the way the circuit looks in Gemma, like a really small model, is extremely similar to the way that it looks like a huge model.

That in itself is, I think, a pretty novel discovery.

It's like, oh, you have these models that are super different.

If you look at their evals or if you just try to use them, they're just very clearly different.

But for this one task, for this one thing, actually, the way that they do this multi-step reasoning is the same way they actually do the multi-step reasoning.

In the notebook, there's both other examples of fun things that we looked at that I think can spike your interest if you're new to thinking about this stuff.

And at the end of the notebook that's linked in the Read Me, there's three examples of random cases that we haven't solved or we haven't labeled that have a graph precomputed for you.

And you could just look at it and try to figure out what's happening.

And by figure out what's happening, what we mean is-- we might do a quick demo here, but it's kind of like, look at these representations, try to understand, OK, what is the computation the model is doing?

And then part of the release also lets you run experiments to verify that you write.

So if you think that, ah, the model first thinks about Texas in this case, you can also just stop it from thinking about Texas and see if that damages it.

And so the tools to do that are available.

And so I would say that's the first thing is just-- I think the hope is there are a lot of behaviors that models do way more than any single group has time to explore.

And so the hope is, hey, pick a behavior that you think is interesting and try to understand what's happening and try to ground it out.

And it's this baseline thing and maybe the thing that I'm most excited about with this release.

But then the other thing I do want to mention, parts two and three are just-- we also hope that other groups and interesting researchers can just use this to extend the method.

If you have an idea about how to do this better, the whole code to make this graph is open source.

Take a look at it and just try to play with it, try to find different ways to create these graphs and also extend it to other models.

There are many different models.

And so part of making this work on any models, you have to train the replacement model, which, again, there is code for it and there's other groups working on.

That's also something that if you're excited about, you could say, OK, cool, well, I want this to work.

I'm like another open model.

And you could add it if you're more into the engineering or the ML engineering side of things.

Yeah, we actually get into a little bit about how you guys do the extra data vid stuff that makes your blog post pop so much.

Should we share the screen a little bit and dive in?

I think you guys prep some examples.

Totally.

Yeah, yeah.

It's just like there's nothing better than the creator of the tool walking through the tool.

And we might as well capture that so that people who actually want to do this can follow along.

Yeah.

That makes sense.

Let me just actually share my screen.

One little experiment, I basically cloned the repo, threw it into Cloud Code, and was like, deal with this.

Let's try it end to end.

So would recommend.

Cloud Code is very good at using this.

Basically also, if you're just trying to get started, the circuit tracing tutorial notebook, very good.

That kind of goes over all the high level.

And then shout out Cloud Code.

Try it out.

It works very well on this.

That's awesome to hear.

Actually, I might just open the notebook first, just quickly walk through the illustrations.

But yeah, you're the second person to tell me that they just had Cloud Code digging initially.

So I'm glad that's working.

The tutorial here is linked at the top of the repo.

And maybe we can link it from the podcast.

But essentially, it walks you through how to think about graphs.

And so it links to these circuits.

So here, this is the two step reasoning that we're talking about.

This is kind of like a schematic of it, where it's like the capital of the state of Dallas.

And it's like, ah, it has to think of Texas and Austin.

But the notebook links you to all of these circuits here.

And this is kind of the thing that you can play with.

So this is the UI on Neuronpedia that hosts this.

And that lets you create any circuit.

So here, we could explore the circuit.

And if you open the notebook, you can explore it.

I'm realizing that I switched tabs.

I'm not showing it.

OK.

There we go.

Can you see the circuit now?

I think so.

OK, cool.

But you can make a new graph super easily and quickly.

And so maybe this is the most fun things.

When I was playing with, right before joining this call, it turns out that podcast guests are very formulaic.

And so if you say, thanks for having me on the whatever-- Gemma seems to have pretty consistently guessed that you're on a podcast.

Which makes sense, right?

Why would you say, thanks for having me on the block?

And so here, we can try to say, like, oh, OK.

How does Gemma know to complete the sentence with, thanks for having me on the latent space podcast?

And so here, the way you generate a graph is you type a sentence where the next word is the thing that you're interested in.

And then you kind of try to explain how the model got to the next word.

So here, you can give it a name.

And then you can mostly just not worry about any of these parameters, I think, if you're just playing with it.

And you can click Start Generation.

And this one-- What this generates, like, something important for people to know is that these are trained on base models, right?

So they're not chat models.

So basically, when you train these models, they're just trained to predict next token.

And they don't have that user assistant chatbot flow.

So they're prompted in a way such that the output should basically just be the next word.

Yeah, you kind of want to think about it as, like, maybe the prompt or the text you're giving is like the text of a book or an article rather than a conversation, where it's like, what is a sentence where if you were to read it in a book, the next word would be sort of like the interesting one.

Yeah.

You can click on it.

So it takes a little bit of time to load because there's just a bunch of data.

So what we're going to show you here is basically almost every single feature that activates in the model, the features are these intermediate representations.

And at the bottom, there's the prompt.

So here it's like, thanks for having me on the latent space.

And at the top, you can see what the model sort of output.

So it's most likely output is it's pretty confident that we're talking about a podcast.

And it has some random stop tokens, blog, show, and then some stuff that I think makes less sense, but also like these are small models.

And so sometimes they say random stuff.

And so the way that you could then explore this would be like, OK, so the model says podcast.

So why does it say podcast?

So you can click on this output and say, what are the features, again, these intermediate representations that have an input to this?

So it seems like there's features at-- here, this is the layer, like layer 18, that already are about podcast episodes.

You can know this because the features have a label.

But also, if you want, you can look at the feature itself here.

And here, you can see that this shows you other text of the feature is active over, and it's just like text about podcasts.

So that's a way that you can also understand what the features are.

And then you can keep going back.

So it's like, OK, so it's at podcast here because of this podcast feature.

Where did that come from?

And it's like, oh, it comes from words related to podcasts, words associated with podcasts, as well as an interview feature, and also just the word on.

So there's a bias.

If you're saying, blah, blah, blah, I mean on, that slightly increases the chance that you're talking about a podcast at all.

And you can keep going back and explore the graph interactively.

I would say that the way to do it-- and we talked about this on the longer version of the podcast, but it's like chasing from the interesting outputs back or from the interesting input forward.

There are many nodes on these.

I wouldn't recommend looking at all of them.

You can also prune them a little more aggressively here if this is too busy.

And this shows you only the most important ones, and you can be pretty extreme with it if you want.

Or you can show the whole thing and then be super overwhelmed.

Once you do this, you can then group your nodes into similar ones to make a graph.

I actually made this little summary earlier, so I can just share that top.

So this is the exact same graph, but just before hopping on, I did a few groups.

So this is the same thing, podcast.

It's like, oh, there's a bunch of nodes that are podcast episodes.

It's just a bunch of things we're discussing podcast.

There's a note about expressing gratitude that amplifies that you're on an interview or a podcast.

So one fun experiment you could do here is like, oh, what happens if I mess with this?

If I mess with the, oh, this person is grateful to be on, and this person is on, does it think you're on something else?

Maybe there are things that you could be on that you're not grateful for, or you're having me on trial or something.

I don't know.

That could be one interesting experiment to see what the causal effect of this is.

And again, you could label it more and explore it more.

And this UI, the whole point is for it to be snappy and quick.

So you can just generate a bunch of graphs pretty easily.

Like maybe this wasn't exactly what you wanted.

So you're like, I'm super unhappy to be on the latent space.

And then you can see what it completes for that or whatever.

And you can just continuously play with it and get a better sense for your hypotheses.

Oftentimes, you want different prompts, different examples that are similar to get a sense for it.

And then if you're really curious and you want to dig in more, that's when I would recommend going back to the code base and some of the notebooks.

Maybe one last thing I'll say on that is that the notebooks themselves, they can all be run on Google Colab.

And all of the code, as far as we can tell, we've tested all the notebooks, just runs on Colab.

And so that means that you don't need-- on the free tier, to be clear-- you don't need an expensive GPU.

You can just run this and run your interventions and play with it.

So in this notebook in particular, the intro one, we show you how to do these interventions.

And here we're like, what happens if we turn this node off?

And what happens if we turn that one off?

And what happens if we turn this one off?

And what happens if we inject one from one prompt into another one?

And so I think that's the deeper dive trying to understand the mechanism better.

But if you're just trying to even get a sense at all of, how does the model do x?

You just generate a graph and take a look at it.

Incredible, very cool.

Is there-- when I look at the graph, is there's a thought in my mind about maybe this is too easy, too perfect.

And one version of this is there's supposed to be superposition.

And here there's no superposition, kind of.

Well, there is superposition.

And we're sort of like-- so maybe I can share the graph again and answer your question, which I think is like, what are we hiding here?

Where are the skeletons?

Yeah.

This is like-- it's too clean.

I'm like-- yeah.

So maybe a good example is-- and we're going to make this slightly less overwhelming here-- is like, OK, so you look at this graph and you say, yeah, we don't actually understand how models work fully.

So what are you hiding here?

And the thing that's important to note here is-- I didn't say this explicitly, but the layers are arranged here.

And so let's just look at one layer.

So for this layer, what we're saying is the only thing that is happening, or that's important enough, is this one feature, which is just one small direction in the model space, right?

Like one dimension we've pulled out of superposition, or let's say that for now.

But then also there's these diamonds.

And these diamonds are errors.

We talked about them on the longer podcast, but they're just like, when you train these replacement models to replace them in the model computation, you successfully replace some of it.

And then some of it you fail to replace.

And so this is everything that we don't understand.

And so that means that sometimes if you look at an input, like this guy's input, you'll see a bunch of errors here as the input.

And so essentially, there's some graphs and some examples where if most of the stuff that you see is these errors, basically that just means like, hey, for this prompt, we were not able to explain that part of the computation.

And so at least that part is like an explicit-- sort of like we show it in your face where it's like, here's what we don't understand.

So you can sort of see what we don't understand.

There's also, I will say, one more thing.

There's a bunch more stuff that can get you.

And that's in the paper.

But one example here that I'll just say is like, these are just MLPs.

So the model has both attention heads and multilayer perceptrons MLPs.

We don't just do it.

We completely ignore attention.

Or we don't try to decompose it at all.

So there are some prompts where all of the interesting stuff is attention.

And here, you're just not seeing it at all.

The way that it's materialized is like, you have an edge from here to here.

And some attention head did a bunch of stuff.

You don't know what it is.

And so that's also the part that we're sort of not explaining.

So there's definitely-- yeah, I don't want to make the claim that we explain everything.

I think the correct way to think about this is like, if you look at a prompt and you can, by tracing through these, not hit any errors, hit nodes that make sense, and build up a reasonable hypothesis, and then when you test it with interventions, it works.

You've at least understood some, and presumably a reasonable proportion of the computation.

If your interventions are working, that means that the thing you found is not just a side thing.

It's part of the main thing that the model is doing.

Then the question is, how often does it happen versus how often do you just hit these errors or are you confused?

And I think that's just sort of what works and what doesn't summary here.

Can you see?

I mean, congrats on this work.

I know you're low on sleep because you worked really hard on shipping it and you're a perfectionist.

I just think-- Yeah, go ahead.

Sorry.

I'll just say that the actual brunt of the work here is like-- Your fellows.

Yeah, yeah, yeah.

I mostly just like coordinated things left and right, but they sort of did all of the implementation, as well as focused on the neuron PD at Decode Research.

I also did the lion's share of the work here to actually have the front end UI.

I'll just say, Veeboo and I were at the GoodFire meetup yesterday, where there were a lot of interpretability folks.

I was shocked at, honestly, how young most interpretability people and work are.

And this is a very young field, exactly like you say in the podcast.

There's a lot of fresh green grass here to tread.

And it's just really inspiring.

Veeboo, do you have any other final thoughts or comments?

Yeah, no, I think there's just a lot of open work to be done.

And we talk about this in the podcast, too.

And just to reiterate how good the tooling that you guys put out is, even the fact that without diving into any code, you can enter in a prompt and start to play through these circuits in minutes, it's pretty incredible.

I could share another one, actually.

So I was doing this with Pomski, and I finally got it to work.

So our guest host of the episode is Mochi, my little dog.

She's our distilled husky.

So she's on the podcast later.

And I basically put in-- I had to guide it quite a bit, but my prompt is, a Pomski is a small dog that's a breed of a husky and a.

And then I'm expecting it to put out Pomeranian or Pom.

Let me share my screen real quick.

And then we can kind of dig through.

This is me like-- By the way, her tagline-- yeah, while you put it out, her tagline is officially Mochi the interpretability husky.

It's a dig.

For today.

We're going to change our tagline every episode.

It feels a little weird.

We're digging deep into what Mochi is.

But basically, this is me, like, no background, like, two minutes, and just put in a phrase.

And now I get to play around with features, right?

So this is also called Please with Foreses, because I tried a few Poms.

It's OK.

It's OK.

We struggle.

It only took a few minutes, though.

So Pomski is a small dog breed that's a mix of a husky and a.

And then the most probable output, now it says Pom.

So OK, let's dig into what some of these are.

I'm basically just going, like, fresh, haven't done this before.

But words related to animals, their emotions, their health, we have a feature for dog, golden lab, mentioned dog breeds, especially high maintenance.

This is basically like AGI.

It knows Pomski is our high maintenance.

It's figured it out.

But realistically, as I dig through these features, I can start to pin them, layer them through mentions of garbage and waste.

No, that's not nice.

That's not nice.

But basically-- Yeah, interesting.

And this is already me pruning out most of the features.

As I open it up, it talks about different things like dog breeding.

What else?

Related to animal welfare.

So like, and then you can dig through all this.

There's just so many things that, like, you know, this is in a matter of minutes.

I basically made a graph, put in a sentence, and now I have an output.

And I can traverse through what are different things.

OK, animal science, right?

So this breed is relatively new.

It's not that common that big huskies and little Pomeranians naturally have offspring.

But you know, let's like dig through animal science versions of this.

And then we have interesting little features.

So it's very easy for people to kind of get a different understanding of what goes on throughout layers in models, you know?

But that's just my fun little experiment of getting it to work.

Oh, yeah.

And I think like, you know, one thing that I would do, if you were curious, or maybe I'm just going to try to bait some listeners into doing it, is like, can you be like, OK, let's try to trace why it said Pomeranian here.

And maybe there's like some of it is about like dog breeds.

And some of it is about specific characteristics of a husky.

And then you can ask the same question.

So if you're thinking about the sub-minice of husky, you try some other dog breed.

And then try to see if you understood it this circuit well.

And if you identified where it's thinking about huskies or where it's thinking about breeding two different breeds, then you should be able to swap these in and out and get it to kind of say whatever you want.

And if you didn't, then maybe there's something complicated going on.

But yeah, very cool that you got this going on so quick.

That's the whole goal.

That's super exciting.

Yeah.

And like, you know, this was like five minutes of just playing around.

And there's stuff to learn there, right?

What happens with dog breeding?

What are traits of these dogs?

And then, you know, the next step for me would basically be let's try clamping some of these features up or down.

Let's do different breeds and see if it makes sense, right?

So if I have husky traits and a different mix, and then, you know, can I get out what's going on?

But it also shows internally that there's more than just token completion of, you know, this plus this equals this.

No, it has some understanding of characteristics, right?

Like this is a pretty stubborn dog.

It has a stubborn feature, pretty high up that activates.

So very, very cool stuff.

I think it'll be cool when we apply this to more serious topics.

Like right now, when it comes to little M-E vowels, right?

We have pretty straightforward evals, right?

Like how good does it do on math?

Can it write code?

Does stuff compile?

But we don't have like vibes-based heuristic evals, right?

So like does it understand different queries?

Should it be concise?

Should they be verbose?

Can we kind of trace through how it gives responses to this stuff?

And then like the other part is, you know, as we go past base models, how does this happen for different phases of models, right?

So if I have a base Gemma and I have a chat model, what are differences in their attributions, right?

What happens kind of in that diff of training?

So that's kind of one of my little interests in Meckinterk.

What happens as we do more training?

What are we really changing?

Totally, yeah.

You can think about comparing different models.

And for me, different models are either like Gemma versus some other model or like early Gemma versus late Gemma and pre-training or like fine-tuned versus not fine-tuned.

I think there's also a sense in which like somebody yesterday was telling me like, oh, that's fun.

I've been playing with it on like the like sort of like weird riddles that the models get wrong.

Like you're not limited to studying what the model can do, right?

Like if the model's failing at something like, you know, counting the number of letters in strawberry or whatever, you could just try that and try to figure out the circuit for like, well, it's getting this wrong.

Like why?

Maybe you can see in its representation that it's like, thinking about something obviously incorrect, right?

And so I think that that's also like a fun thing to play with.

I think that's it for our little intro chat and coverage of the open sourcing.

Let's dive right into the episode next.

But Emmanuel, you're amazing work and I'm so inspired.

And also just like I think this puts a human face on the interpretability work.

I think it's very important.

And we'd love to keep doing this.

Whatever you got next coming up.

Well, yeah, thanks for having me.

Again, I should say, cool to put a face on it, but definitely want to call.

This is like a huge team of people with me.

I'm just a talking head here.

And paper lead, you know.

You did the work.

Take credit.

I think that like, yeah, happy to talk about more interpretive things.

And also like feel free to reach out to me.

I'm like findable if you're listening to this podcast and you have like questions about stuff that's broken or if this brings up like experiment ideas.

I definitely want more people playing with this.

So yeah, thanks for having me.

Hope that inspires the folks.

All right, we are back in the studio with a couple of special guests.

One, Vibhu, our guest co-host for a couple of times now, as well as Mochi the Distilled Husky is in the studio with us.

You asked some very pressing questions.

As well as Emmanuel-- I didn't get your last name.

Amason?

Yep.

Is that Dutch?

Is that-- It's actually German.

German?

Yeah.

You are the lead author of a fair number of the recent Meccan Terp work from an topic that I've been basically calling transformer circuits, because that's the name of the publication.

Yeah.

Well, to be clear, transformer circuits is the whole publication.

I'm the author on one of the recent papers, Circuit Tracing.

Yes.

And people are very excited about that.

The other name for it is like Tracing the Thoughts of LLMs.

There's like three different names for this work.

But it's all Meccan Terp.

It's all Meccan Terp.

There's two papers.

One is Circuit Tracing.

It's the methods.

One is like the biology, which is kind of what we found in the model.

And then Tracing the Thoughts is confusingly just the name of the blog post for an announcement.

It's for different audiences.

And I think when you produced the two-minute polished video that you guys did, that's meant for a very white audience.

Yeah, that's right.

There's sort of very many levels of granularity at which you can go.

And I think for Meccan Terp in particular, because it's kind of complicated, going from top to bottom, most high level to sort of their nollie details works pretty well.

Yeah.

Cool.

We can get started.

Basically, we have two paths that you can choose, either your personal journey into Meccan Terp or the brief history of Meccan Terp just generally.

And maybe that might coincide a little bit.

I think my-- OK, I could just give you my personal journey very quickly, because then we can just do the second path.

My personal journey is that I was working at Anthropic for a while.

I'd been-- like many people just following Meccan Terp as sort of like an interesting field with fascinating, often beautiful papers.

And I was at the time working on fine tuning.

So like actually fine tuning production models for Anthropic.

And eventually, I got both-- my fascination reached a sufficient level that I decided I wanted to work on it.

And also, I got more excited about just-- as our models got better and better, understanding how they worked.

So that's the simple journey.

I've got a background in ML, kind of like did a lot of applied ML stuff before, and now I'm doing more research stuff.

Yeah, you have a book with O'Reilly.

You're ahead of the AI at Insight Data Science.

Anything else to plug?

Yeah.

Actually, I want to plug the paper and unplug the book.

I think the book is good.

I think the advice stands the test of time.

But it's very much like, hey, you're building AI products, which do you focus on?

It's very different, I guess is all I'll say, from the stuff that we're going to talk about today.

Today is research.

Some of the deepest, weirdest things about how models work.

And this book is, you want to ship a random forest to do fraud classification.

Like here are the top five mistakes to avoid.

Yeah.

The good old days of ML.

I know.

It was simple back then.

You also transitioned into research.

And I think you also did the management.

I feel like there's this monolith of people assuming you need a PhD for research.

Maybe can you give that perspective of how do people get into research?

How do you get into research?

Maybe that gives audience insight into Vivo as well.

Your background.

Yeah, my background was in economics, data science.

I thought LLMs were pretty interesting.

I started out with some basic ML stuff.

And then I saw LLMs were starting to be a thing.

So I just went out there and did it.

And same thing with AI engineering.

You just kind of build stuff.

You work on interesting things.

And now it's more accessible than ever.

Like back when I got into the field five, six years ago, pre-training was still pretty new.

GPT-3 hadn't really launched.

So it was still very early days.

And it was a lot less competitive.

But yeah, without any specific background, no PhD, there just weren't as many people working on it.

But you made the transition a little bit more recently.

So what's your experience been like?

Yeah, I think it has maybe never been easier in some ways.

Because a lot of the field is pretty empirical right now.

So I think the bitter lesson is this lesson that you can just sort of a lot of times scale up compute and data and get better results than thinking-- than if you thought extremely hard about a really good prior inspired by the human brain to train your model better.

And so in terms of definitely research for pre-training and fine tuning, I think it's just sort of like a lot of the bottlenecks are extremely good-- engineering and systems engineering.

And a lot even of the research execution is just about engineering and scaling up and things like that.

I think for Interp in particular, there's another thing that makes it easier to transition to, which is maybe two things.

One, you can just do it without huge access to compute.

There are open source models.

You can look at them.

A lot of Interpapers coming out of programs like Maths are on models that are open source.

You can sort of dissect without having a cluster of 100 GPUs.

Sometimes you can load them on your CPU, on your MacBook.

And it's also a relatively new field.

And so I'm sure we'll talk about there's some conceptual burdens and concepts that you just want to understand before you contribute.

But it's not physics.

It's relatively recent.

And so the number of abstractions that you have to ramp up on is just not that high compared to other fields, which I think makes that transition somewhat easier for Interp if you understand-- we'll talk about all these, I'm sure.

But what features are and what dictionary learning is, you're a long part of the way there.

I think that's also interesting.

Just on the careers point of view, research seems a lot more valuable than engineering.

So I wonder-- and you don't have to answer this if it's a tricky thing-- but how hard is it for a research engineer in anthropic to jump the wall into research?

People seem to move around a lot.

And I'm like, that cannot be so easy.

Like, in no other industry that I know of, you can do that.

Do you know what I mean?

Yeah.

I think I'd actually like-- I'd push back on the research being more valuable than engineering a little bit.

OK.

I think a lot of times, having the research idea is not the hardest part.

Don't hear me wrong.

There's some ideas that are brilliant and hard to find.

But what's hard, certainly on fine tuning and to a certain extent on Interp, is executing on your research idea in terms of making an experiment, successfully having your experiment run, interpreting it correctly.

What that means, though, is that they're not separate skill sets.

So if you have a cool idea, there's kind of not many people in the world, I think, where they can just have a cool idea, and then they have a little minion.

They'll deprecise, being like, here's my idea.

Go off for three months and run this whole-- build this model and train it for hundreds of hours, and then report back on what happened.

A lot of the time, the people that are the most productive, they have an idea.

But they're also extremely quick at checking their idea, finding the shortest path to taking their idea.

And a lot of that shortest path is engineering skills, essentially.

It's just getting stuff done.

And so I think that's why you see people move around.

It's proportionate to your interest.

If you're just able to quickly execute on the ideas you have and get results, then that's really the 90% of the value.

And so you see a lot of transferable skills, actually, I think, from people like-- I've certainly seen hydropics that are just really good at that inner loop.

They can apply it in one team and then move to a completely different domain and apply that inner loop just as well.

Yeah, very cracked, as the kids say.

Shall we move to the history of MechaTurb?

Yeah.

All I know is that everyone starts at Chris Olas's blog.

Is that right?

Yeah, I think that's the correct answer, Chris Olas's blog.

And then distill.pub is the natural next step.

And then I would say, now there's Ferranthropic, there's Transformer Circuits, which we talked about.

But there's also just a lot of MechaTurb research out there from-- I think like Maths is a group that regularly has a lot of research.

But there's just many different labs that put research out there.

And I think that's also just hammer home the point.

That's because all you need is a model and then a willingness to investigate it to be able to contribute to it.

So now there's been a bit of a Cambrian explosion of MechaTurb, which is cool.

I guess the history of it is just models that are not decision trees, models that are either CNNs or, let's say, Transformers, have just this really strange property that they don't give you interpretable intermediate states by default.

Again, to go back to if you were training a decision tree on fraud data for an old school bank or something, then you can just look at your decision tree and be like, oh, it's learned that if you make-- I don't know if this transaction is more than $10,000 and it's for perfume, then maybe it's fraud or something.

You can look at it and say, cool, that makes sense.

I'm willing to ship that model.

But for things like CNNs and like Transformers, we don't have that, right?

What we have at the end of training is just a massive amount of weights that are connected somehow-- activations are connected by some weights.

And who knows what these weights mean or what the intermediate activations mean?

And so the quest is to understand that.

Initially, a lot of it was on a vision models where you have the emergence of a lot of these ideas, like what are features, what are circuits.

And then more recently, it's been mostly-- or not mostly-- yeah, mostly applied to NLP models.

But also, still, there's work in vision and there's work in bio and other domains.

Yeah, I'm on Chris Ola's blog, and he has the feature visualization stuff.

I think for me, the clearest was the vision work where you could have this layer detects edges, this layer detects textures, whatever.

That seemed very clear to me.

But the transition to language models seemed like a big leap.

I think one of the bigger changes from vision to language models has to do with the superposition hypothesis, which maybe is like-- That's the first point models post, right?

Exactly.

And this is sort of like-- it turns out that if you look at just the neurons of a lot of vision models, you can see neurons that are curve detectors or that are edge detectors or that are high-low frequency detectors.

And so you can make sense of the neurons mostly.

But if you look at neurons in language models, most of them don't make sense.

It's kind of like unclear-- or it was unclear where that would be.

And one main hypothesis here is the superposition hypothesis.

So what does that mean?

That means that language models pack a lot more in less space than vision models.

So maybe like a kind of like really hand-waving analogy, right, is like, well, if you want curve detectors, you don't need that many curve detectors.

Each curve detector is going to detect like a quarter or 12th of a circle.

Like, OK, well, you have all your curve detectors.

But think about all of the concepts that like Claude or even GPT-2 needs to know, like just in terms of-- it needs to know about all of the different colors, all the different hours of every day, all of the different cities in the world, all of the different streets on every city.

If you just enumerate all of the facts that a model knows, you're going to get a very, very long list.

And that list is going to be way bigger than the number of neurons or even the size of the residual stream, which is where the models process information.

And so there's this sense in which, oh, there's more information than there's dimensions to represent it.

And that is much more true for language models than for vision models.

And so because of that, when you look at a part of it, it just seems like it's got all this stuff crammed into it.

Whereas if you look at the vision models, oftentimes you could just be like, cool, this is a curve detector.

Yeah.

Vibhu, you have some fun ways of explaining the toy models or superposition concepts.

Yeah, I mean, basically, if you have two neurons and they can represent five features, a lot of the early Mecha Interpreter work says that there are more features than we have neurons.

So I guess my kind of question on this is, for those interested in getting into the field, what are the key terms that they should know?

What are the few pieces that they should follow?

From the anthropic side, we had a toy transformer model.

We first had auto encoders.

No, it is the second paper, right?

Monosubmentation.

Yeah.

What is sparsity in auto encoders?

What are transcoders?

What is linear probing?

What are these kind of key points that we had in Mecha Interpreter?

And just kind of how would people get a quick 0% to 80% of the field?

OK, so 0% to 80%.

And I realized I really stepped myself up for failure because I was like, yeah, it's easy.

There's not that much to know.

So OK, so then we should be able to cover it all.

So superposition is the first thing you should know, right?

This idea that there's a bunch of stuff crammed in a few dimensions.

As you said, maybe you have two neurons and you want to represent five things.

So if that's true, and if you want to understand how the model represents, I don't know, the concept of red, let's say, then you need some way to find out essentially in which direction the model stores it.

So after the sort of superposition hypothesis, you can think of, ah, we also think that basically the model represents these individual concepts.

We're going to call them features.

As like directions.

So if you have two neurons, you can think of it as like it's like the 2D plane.

And it's like, ah, you can have like five directions.

And maybe you would arrange them like the spokes of a wheel.

So they're sort of like maximally separate.

It could mean that you have one concept this way and one concept that's not fully perpendicular to it, but pretty far from it.

And then that would allow the model to represent more concepts than it has dimensions.

And so if that's true, then what you want is you want a model that can extract these independent concepts.

And ideally, you want to do this automatically.

Can we just have a model that tells us, oh, this direction is red.

If you go that way, actually, it's like, I don't know, chicken.

And if you go that way, it's like the declaration of independence.

And so that's what sparse auto encoders are.

It's almost like the self-supervised learning insight version.

In pre-training, it's self-supervised learning.

And here now, it's self-supervised interpretability.

Yeah, exactly.

Exactly.

It's like an unsupervised method.

And so unsupervised methods often still have labels in the end.

Sometimes, I think the term unsupervised-- You form labels by masking.

Yeah, for pre-training, it's like the next token.

So in that sense, you have a supervision signal.

And here, the supervision signal is simply, you take the neurons, and then you learn a model that's going to expand them into the actual number of concepts that you think there are in the model.

So you have two neurons.

You think there's five concepts.

So you expand it to, I think, of dimension five.

And then you contract it back to what it was.

That's the model you're training.

And then you're training it to incentivize it to be sparse.

So there's only a few features active at a time.

And once you do that, if it works, you have this nice dictionary, which you can think as a way to decode the neurons, where you're saying, ah, cool.

I don't know what this direction means.

But I've used my model, and it's telling me that the model is riding in the red direction.

And so that's sort of, I think, maybe the biggest thing to understand is this combination of things.

So we're like, ah, we have two dimensions.

We pack a lot into it.

So we're going to learn an unsupervised way to unpack it and then analyze what each of those dimensions that we've unpacked are.

Any follow ups?

Yeah, I mean, the follow ups of this are also kind of like-- some of the work that you did is in clamping, right?

What is the applicable side of Mecha Interp, right?

So we saw that you guys have great visualizations.

Golden Gate Claude was a cool example.

I was going to say that.

Yeah.

That was my favorite.

What can we do once we find these features?

Finding features is cool, but what can we do about it?

Yeah.

I think there's kind of like two big aspects of this.

One is, yeah, OK.

So we go from a state where, as I said, the model is like a massive weight, so we have no idea what's going on to, OK, we found features.

We found a feature for red, a feature for Golden Gate Claude, or for the Golden Gate Bridge, I should say.

What do we do with them?

And well, if these are true features, that means that they, in some sense, are important for the model, or it wouldn't be representing it.

If the model is bothering to write in the Golden Gate Bridge direction, it's usually because it's going to talk about the Golden Gate Bridge.

And so that means that if that's true, then you can set that feature to zero or artificially set to 100, and you'll change the model behavior.

That's what we did when we did Golden Gate Claude, in which we found a feature that represents a direction for the Golden Gate Bridge, and then we just set it to always be on.

And then you could talk to Claude and be like, hey, Claude, what's on your mind?

What are you thinking about today?

Be like the Golden Gate Bridge.

He'd be like, hey, Claude, what's 2 plus 2?

It'd be like four Golden Gate Bridges, et cetera.

And it was always thinking about the Golden Gate Bridge.

It was like write a poem, and it just starts talking about how it's red, like the Golden Gate Claude.

Golden Gate Bridge, yeah.

That's right.

I think what made it even better is we realized later on that it wasn't really like a Golden Gate Bridge feature.

It was like being in awe at the beauty of the majestic Golden Gate Bridge.

So on top of that, it would really ham it up.

You'd be like, oh, I'm just thinking about the beautiful international orange color of the Golden Gate Bridge.

That was like an example that I think was really striking.

But of sort of like, oh, if you found a space where that represents some computation or some representation in the model, that means that you can artificially suppress or promote it.

And that means that you're starting to understand at a very high level, a very gross level, how some of them all works.

We've gone from I don't know anything about it to like, I know that this combination of neurons is this, and I'm going to prove it to you.

The next step, which is what this works on, is that's kind of like thinking of if maybe you take the analogy of like-- I don't know.

Let's take the analogy of an MRI or something like a brain scan.

It tells you, oh, as Claude was answering, at some point, it thought about this thing.

But it's sort of like vague.

Basically, maybe it's like a bag of words, kind of like a bag of features.

You just have like, here are all the random things it thought about.

But what you might want to know is like, OK, but Claude is doing some processing.

Sometimes to get to the Golden Gate Bridge, it had to realize that you were talking about San Francisco and about the best way to go to Sonoma or something.

And so that's how it got to Golden Gate Bridge.

So there's like an algorithm that leads to it at some point thinking about the Golden Gate Bridge.

And basically, there's like a way to connect features, to say like, oh, from this input, went to these few features, and then these few features, and then these few features, and then that one influenced this one, and then you got to the output.

And so that's the second part.

And the part we worked on is like, you have the features, now connect them in what we call-- or what's called circuits, which is sort of like explaining the algorithm.

Yeah, before we move directly onto your work, I just want to give a shout out to Neil Nanda.

He did Neuronpedia and released a bunch of essays for I think the llama models and the gemma models.

And the gemma models, yeah.

So I actually made Golden Gate Gemma.

Just up the weights for proper nouns and names of places for people and references to the term golden, likely relating to awards, honors, or special names, and that together made Golden Gate.

That's amazing.

Yeah.

So you can make Golden Gate Gemma, and I think that's a fun way to experiment with this.

But yeah, we can move on to-- I'm curious.

I'm curious.

What's the background behind why you ship Golden Gate Claw?

Like, you had so many features.

Just any fun story behind why that's the one that made it?

You know what's funny?

If you look at the paper, there's just a bunch of really interesting features, right?

There's like one of my favorite ones was the psychophantic praise, which I guess is very topical right now.

Very topical.

But you know, it's like you could dial that up, and Claude would just really praise you.

He'd be like, oh, you know, I wrote this poem, like roses are red, violets are blue, whatever.

And he'd be like, that's the best poem I've ever seen.

And so we could have shipped that.

That could have been funny.

Golden Gate Claude was like a pure-- as far as I remember at least, like a pure, just like weird random thing where somebody found it initially with an internal demo of it.

Everybody thought it was hilarious.

And then that's sort of how it came out.

There was no-- nobody had a list of top 10 features we should consider shipping, and we picked that one.

It was just kind of like a very organic moment.

No, like the marketing team really leaned into it.

Like, they mailed out pieces of Golden Gate for people in Europe, I think, or ICML.

Yeah, it was fantastic marketing.

The question obviously is like if OpenAI had invested more interpretability, would they have got the GPT-4.0 update?

But we don't know that for sure because they have Interp teams.

Yeah, I think also like for that one, I don't know that you need Interp.

Like it was pretty clear cut talking to the model.

I was like, oh, that model is really gassing me up.

And then the other thing is can you just like up, write good code, don't write bad code, and make Sonda 3.5?

And it feels too easy, too free.

Is steering that powerful that you can just like up and down features with no trade-offs?

There was like a phase where people were basically saying, you know, 3.5 and 3.7 are just now-- Because they came out right after this.

And for the record, like that's been debunked.

Yeah, it has been debunked.

But you know, it had people convinced that what people did is they basically just steered up and steered down features.

And now we have a better model.

And this kind of goes back to that original question of, right, like, why do we do this?

What can we do?

Some people are like, I want tracing from a sense of, you know, legality.

Like, what did the model think when it came to this output?

Some people want to turn hallucination down.

Some people want to turn coding up.

So like, what are some-- like, whether it's internal, what are you exploring that?

Like, what are the applications of this?

Whether it's open-ended of what people can do about this, or just like, yeah, why do Meck and Terp, you know?

Yeah, there's like a few things here.

So like, first of all, obviously, this is, I would say, on the scale of the most short term to the most long term, like pretty long term research.

So in terms of like applications compared to, you know, like the research work we do on like fine tuning or whatever, Interp is much more, you know, sort of like a high risk, high reward kind of approach.

With that being said, like, I think there's just a fundamental sense in which Michael Nielsen had a post recently about how like knowledge is dual use or something.

But just like knowing how the model works at all feels useful.

And you know, it's hard to argue that if we know how the model works and understand all the components that won't help us like make models that hallucinate less, for example, or they're like less biased.

That seems, you know, if like at the limit, yeah, that totally seems like something you do using basically like your understanding of the model to improve it.

I think for now, as we can talk about a little bit with like circuits, there's like, we're still pretty early on in the game, right?

And so right now, the main way that we're using Interp early is like to investigate specific behaviors and understand them and gain a sense for what's causing them.

So like one example that we can talk about later, we can talk about now, but in the paper, we investigate jail breaks and we try to see like, why does a jailbreak work?

And then we realize as we're looking at this jailbreak that part of the reason why Claude is telling you how to make a bomb in this case is that it's like already started to tell you how to make a bomb and it would really love to stop telling you how to make a bomb.

But it has to first finish its sentence.

Like it really wants to make correct grammatical sentences.

And so it turns out that like seeing that circuit, we were like, ah, then does that mean if I prevent it from finishing its sentence, the jailbreak works even better and sure enough it does.

And so I think like the level of sort of practical applications right now is of that shape.

So like understanding either like quirks of a current model or like how it does tasks that maybe we don't, we don't even know how it does it.

Like, you know, we have like some planning examples where we had no idea it was planning and we're like, oh God, it is.

That's sort of like the current state we're at.

- I'm curious internally how this kind of feeds back into like the research, the architecture, the pre-training teams, the post-training, like is there a good feedback loop there?

Like right now there's a lot of external people interested, right?

Like we'll train an essay on one layer of llama and probe around, but then people are like, oh yeah, how does this have much impact?

People like clamping, but yeah, as you said, you know, once you start to understand these models have this early planning and stuff, how does this kind of feedback?

- I don't know that there's like much to say here other than like, I think we're definitely interested in conversely like making models for which it's like easier to interpret them.

So that's also something that you can imagine sort of like working on, which is like making models where you have to work less hard to try to understand what they're doing.

- So like the architecture?

Okay, yeah, so I think there was a less wrong post about this of like, there's a non-zero amount of sacrifice you should make in current capabilities in order to actually make them more interpretable because otherwise they will never catch up.

- You know, there's this sort of sense in which like right now we take the model and then the model's the model and then we post hoc, do these replacement layers to try to understand it.

But of course when we do that, we don't like fully capture everything that's happening inside the model, we're capturing like a subset.

And so maybe some of it is like, you could train a model that's sort of like easier to interpret negatively.

And it's possible that like, you don't even have that much of like a tax in that sense.

And you can just sort of like either like train your model differently or do like a little post hoc step to like sort of like untangle some of the mess that you've made when you train your model, right?

Make it easier to interpret.

- The hope was pruning would do some of that, but I feel like that area of research has just died.

What kind of pruning are you thinking of here?

- Just pruning your network.

- Yeah.

- Pruning layers, pruning connections, whatever.

- Yeah, I feel like maybe this is something where like superposition makes me less hopeful or something.

- Exactly, 'cause you don't know.

Like that like seventh bit might hold something.

- Well, right.

And it's like on each example, maybe this neuron is like at the bottom of like what matters, but actually it's participating like 5% to like understanding English, like doing integrals and you know, like whatever, like cracking codes or something.

And it's like because that represents just like distributed over it, you kind of like, when you naively prune, you might miss that.

I don't know.

- Okay, so then this area of research in terms of creating models that are easier to interpret from the start, is there a name for this field of research?

- I don't think so.

And I think it was like very early and it's mostly like a dream.

- Just in case there's a thing people want to double click on.

- Yeah, yeah, yeah.

- I haven't come across it.

I think the higher level, it's like Dario recently put out a post about this, right?

Why mech interprets so important.

You know, we don't want to fall behind.

We want to be able to interpret models and understand what's going on.

Even though capabilities are getting so good, it kind of ties into this topic, right?

Like we want models to be slightly easier to interpret so we don't fall behind so far.

- Well, yeah.

And I think here, like just to talk about the elephant and the room or something, like one big concern here is like safety, right?

And so like as models get better, they are going to be used more and more places.

You know, it's like, you're not going to have your, you know, we're vibe coding right now.

Maybe at some point, well, that'll just be coding.

It's like, Claude's going to write your code for you and that's it.

And Claude's going to review the code that Claude wrote and then Claude's going to deploy to production.

And at some point, like as these models get integrated deeper and deeper into more and more workflows, it gets just scarier and scarier to know nothing about them.

And so you kind of want your ability to understand the model to scale with like how good the model is doing, which that itself kind of like tends to scale with like how widely deployed it is.

So as we like deploy them everywhere, we want to like understand them better.

- The version that I liked from the old super alignment team was weak to strong generalization or weak to strong alignment, which that's what super alignment to me was.

And that was my first aha moment of like, oh yeah, at some point, these things will be smarter than us.

And in many ways they already are smarter than us.

And we rely on them more and more.

We need to figure out how to control them.

And this is not like an Eliezer, Yekowski, like aha thing, it's just more like, we don't know how these things work.

Like how can we use them?

- Yeah, and like you can think of it as, there's many ways to solve a problem.

And some of them, if the model is solving it in like a dumb way or in like memorized one approach to do it, then you shouldn't deploy it to do like a general thing.

Like you could look at how it does math and based on your understanding of how it does math, you're like, okay, I feel comfortable using this as a calculator or like, no, it should always use a calculator tool because it's doing math in a stupid way and extend that to any behavior, right?

Where it's just a matter of like, think about it if like you're like in the 1500s and I give you a car or something, and I'm just like, cool, like this thing, when you press on this, like it accelerates, when you press on that, like it stops, you know, this steering wheel seems to be doing stuff, but you knew nothing about it.

I don't know if it was like a super faulty car and it's like, oh yeah, but if you ever went above 60 miles an hour, like it explodes or something, like you probably would be sort of like, you'd want to understand the nature of the object before like jumping in in it.

And so that's why we like understand how cars work very well because we make them.

LLMs are sort of like, and ML models in general are like this very rare artifact where we like make them but we have no idea how they work.

- We evolve them, we create conditions for them to evolve and then they evolve and we're like, cool, like, you know, maybe you got a good run, maybe we didn't.

- Yeah.

- Don't really know.

- Yeah, the extent to which you know how it works is you have your like eval and you're like, oh, well, seems to be doing well on this eval.

And then you're like, is this because this was in a training set or is it like actually generalizing?

I don't know.

- My favorite example was somehow C4, the common, the colossal clean corpus did much better than common crawl, even though it filtered out most of this, like it was very prudish.

So it like filters out anything that could be considered obscene, including the word gay.

But like somehow it just like, when you add it into the data mix, it just does super well.

And it's just like this magic incantation of like, this recipe works, just trust us.

We've tried everything, this one works.

So just go with it.

- Yeah.

- It's not very satisfying.

(laughs) - No, it's not.

The side that you're talking about, which is like, okay, like how do you make these?

And it's kind of unsatisfying that you just kind of make the soup and you're like, oh, well, you know what?

My grandpa made the soup with these ingredients.

I don't know why, but I just make the soup the way my grandpa said.

And then like, one day somebody added, you know, cilantro.

And since then we've been adding cilantro for generations.

And you're like, this is kind of crazy.

- That's exactly how we train models though.

- Yeah, yeah.

So I think there's like a part where it's like, okay, like let's try to unpack what's happening.

You know, like the mechanisms of learning, like how, how are models learning like one of them, I guess, I guess we skipped over it, but like one of the things were like induction heads, you know, like understanding what induction heads are, which are attention heads that allow you to look at in your context, the last time that something was mentioned and then repeat it.

It's like something that happens.

It seems to happen in every model.

And it's like, oh, okay.

That makes sense.

That's how the model like is able to like repeat text without dedicating too much capacity to it.

- Let's get it on screen.

So if you can see visuals of the work you guys put out is amazing.

- Oh yeah, we should talk a little bit about the behind the scenes of that mechanism, but let's, let's, let's finish this off first.

- Totally.

But just really quickly, I don't think we should spend too long on it.

I think it's just like, if you're interested in Meck and Terp, we talked about superposition and I think we skipped over induction heads.

And that's like, you know, kind of like a really neat basically pattern that emerges in many, many transformers where essentially they just learn.

Like one of the things that you need to do to like predict text well is that if there's repeated texts at some point, somebody said Emmanuel Mason, and then you're like on the next line and they say Emmanuel, very good chance.

It's the same last name.

And so one of the first things that models learn is just like, okay, I'm just gonna like look at what was said before and I'm gonna say the same thing.

And that's induction heads, which is like a pair of attention heads that just basically look at the last time something was said, look at what happened after, move that over.

And that's an example of a mechanism where it's like, cool.

Now we understand that pretty well.

There's been a lot of follow up research on understanding better, like, okay, like in which context do they turn on?

Like, you know, there's like different like levels of abstraction.

They're like induction heads that like literally copy the word and there's some that copy like the sentiment and other aspects.

But I think it's just like an example of slowly unpacking, you know, or like peeling back the layers of the onion of like, what's going on inside this model?

Okay, this is a component is doing this.

So induction headless was like the first major finding.

It was a big finding for NLP models.

Yeah.

I often think about the edit models.

So Claude has a fast edit mode.

I forget what it's called.

Opening out has one as well.

And you need very good copying every area that needs copying.

And then you need it to switch out of copy mode when you need to start generating.

Right.

And that is basically the production as version of this.

Yeah.

Yeah.

And it turns out that, you know, you need to select a model that's like smart enough to know when it needs to get out of copy mode.

Right.

Which is like it's fascinating.

It's faster.

It's cheaper.

You know, as bullish as I am on canvas, basically every AI product needs to iterate on a central artifact.

And like if it's code, if it's a piece of writing, it doesn't really matter.

But you need that copy capability that's smart enough to know when to turn it off.

That's why it's cool that induction are at different levels of abstraction.

Like sometimes you need to editing some code.

You need to copy like the general structure.

It's like, oh, like the last like this other function that's similar.

It first takes like, you know, I don't know, like abstract class.

And then it takes like an and so I need to like copy the general idea.

But it's going to be a different abstract class and a different int or something.

Yeah.

Cool.

Yeah.

So tracing.

Oh, yeah.

Should we jump to circuit tracing?

Sure.

I don't know if there's anything else you want to cover.

No, no, no.

We have space for it.

Maybe I'll do like a really quick TLDR of these two recent papers.

OK.

Insanely quick.

So we talked about these features that we detect and what we said is like, OK, but we'd like to connect the features to understand like the inputs to every features and the opposite features and basically draw a graph.

And this is like if I'm still sharing my screen, the thing on the right here where like that's the dream we want, like for a given prompt, what were all of the things like all of the important things happen in the model?

And here's like, OK, it took in these four tokens.

Those activated these features, these features activate these other features and then these features activate the other features.

And then all of these like promoted the output.

And that's the story.

And basically we're like the work is to sort of use dictionary learning and these replacement models to provide a explanation of like sets of features that explain behavior.

So this is super abstract.

So I think immediately maybe we can like just look at one example.

I can show you one, which is this one.

The reasoning one.

Yeah.

Yeah.

Two step reasoning.

I think this is already this is like the introduction example, but it's already like kind of fun.

So the question is, you ask the model something that requires it to take step of reasoning in its head.

So you say, you know, fact, the capital of the state containing Dallas is.

So to answer that, you need one intermediate step, right?

You need to say, wait, where's Dallas?

Isn't Texas?

OK, cool.

Capital Texas, Austin.

And this is like in one token, right?

It's going to after is it's going to say Austin.

And so like in that one forward pass, the model needs to extract to realize that you're asking it for like the capital of a state to like look up the state for Dallas, which is Texas, and then to say Austin.

And sure enough, this is like what we see is we see like in this forward pass, there's a rich sort of like inner set of representations where there's like it gets capital state in Dallas and then boom, it has an inner representation for Texas and then that plus capital leads it to like say Austin.

I guess one of the things here is like we can see this internal like thinking step, right?

But a lot of people say is like, is this just memorized fact, right?

Like I'm sure a lot of the pre-training that this model is trained on is this sentence shows up pretty often, right?

So this shows that no, actually, internally throughout, we do see that there is this middle step, right?

It's not just memorized.

You can prove that it generalized.

Yeah, so so so that's exactly right.

And I think like you you hit the nail on the head, which is like this is what this example is about.

It's like, oh, if this was just memorized, you wouldn't need to have an intermediate step at all.

You'd just be like, well, I've seen the sentence like I know it comes back.

Right.

But here there is an intermediate step.

And so you could say like, OK, well, maybe it just has the step, but it's memorized anyways.

And then the way to like verify that is kind of like what what we do later in the paper and for all of our examples is like, OK, we claim that this is like the Texas representation.

Let's get another one and replace it.

And we just change like that feature in the middle of the model and we change it to like California.

And if you change it to California, sure enough, it's a Sacramento.

And so it's like this is not just a like byproduct, like it's memorized something.

And on the side, it's thinking about Texas.

It's like, no, no, no.

This is like a step in the reasoning.

If you change that intermediate step, it changes the answer.

Very, very cool work.

Underappreciated.

Yeah.

OK, sure.

I have never really doubted.

I think there's a lot of people that are always criticizing LMS, this stochastic parrots.

This pretty much disproves it already.

Like we can move on.

Yeah, I mean, I think I think there's a lot of examples that I will say we can go through like a few of them and like show an amount of depth in the intermediate states of the model.

That makes you think like, oh, gosh, like it's doing a lot.

I think maybe like the poems.

Well, definitely the poems.

But even for this one, I'm going to like scroll in this very short paper to like medical diagnoses.

I don't even know the word count because there's so many like embedded things in there.

Yeah, it's too dangerous.

We can't look it up.

It blows.

It's so beautiful.

Look at this.

This is like a medical example that I think shows you again, this is in one forward pass.

The model is like given a bunch of symptoms and then it's asked not like, hey, what is what is the like disease that this person has?

It's asked like if you could run one more test to determine it, what would it be?

So it's even hard, right?

It means like you need to take all the symptoms.

They need to like have a few hypotheses about what the disease could be.

And then based on your hypotheses, say like, well, the thing that would like be the right test to do is X.

And here you can see these three layers, right?

Where it's like in one forward pass, it has a bunch of like, oh, these are symptoms.

Then it has the most likely diagnosis here, then like an alternate one.

And then based on the diagnosis, it like gives you basically a bunch of things that you could ask.

And again, we do the same experiments where you can like kill this feature here, like suppress it.

And then it asks you a question about the second, the second option it had.

The reason I show it is like, man, that's like a lot of stuff going on.

Like for one forward pass, right?

It's like specifically if you expected it to like, oh, what it's going to do is it's just like seeing similar cases in the training.

It's going to kind of like vibe and be like, oh, I guess like there's that word and it's going to say something that's related to like, I don't know, headache, you know, and I kind of like really have this like, no, no, no.

It's like activating many different distributed representations, like combining them and sort of like doing something pretty complicated.

And so, yeah, I think I think it's funny because in my opinion, that's like, yeah, like, oh, God, stochastic parts is not something that I think is like appropriate here and I think there's just like a lot of different things going on and there's like pretty complex behavior at the same time.

I think it's in the eye of the beholder.

I think like I've talked to folks that have like read this paper and I've been like, oh yeah, this is just like a bunch of kind of like heuristics that are like mashed together, right?

Like the models is doing like a bunch of kind of like, oh, if high blood pressure than this or that.

And so I think there's there's sort of like an underlying question that's interesting, which is like, okay, now we know a little bit of how it works.

This is how it works.

Like now you tell me if you think that's like impressive.

If you think that if you trust it, if you think that's sort of like something that is that is sufficient to like ask it for medical questions or whatever.

I think it's a way to adversarially improve the model quality.

Because once you can do this, you can reverse engineer what would be a sequence of words that to a human makes no sense or lets you arrive at the complete opposite conclusion, but the model still gets tripped up by.

Yeah.

And then you can just improve it from there.

Exactly.

And this gives you a hypothesis about like you like specifically imagine if like one of those was actually like the wrong symptom or something.

You'd be like, oh, it's weird that the liver condition like, you know, upways this other example.

That doesn't make sense.

Okay.

Let's like fix that in particular.

Exactly.

You sort of have like a bit of insight into like how the model is getting to its conclusion.

And so you can see both like, is it making errors, but also is it using the kind of reasoning that will lead it to errors?

There's a thesis.

I mean, now it's very prominent with the reasoning models about model depth.

So like you're doing all this in one pass, but maybe you don't need to.

Because you can do more passes.

And so people want shallow models for speed, but you need model depth for this kind of thinking.

Yeah.

Is there a Pareto frontier?

Is there a direct trade-off?

Yeah.

I mean, would you prefer if you had to make a model and like, you know, shallow versus deep?

There's a chain of thought faithfulness example, before I show it, I'm just going to go back to the top here.

So when the model is sampling many tokens, if you want that to be your model, you need to be able to trust every token it samples.

So like the problem with models being autoregressive is that like, if they like at some point sample a mistake, then they kind of keep going conditioned on that mistake, right?

And so sometimes like you need backspace tokens or whatever.

Yeah, yeah, yeah.

And error correction is like notably hard, right?

If you have like a deeper model, maybe you have like fewer COT steps, but like your steps are more likely to be like robust or correct or something.

And so I think that that's one way to look at the trade-off.

To be clear, I don't have an answer.

I don't know if I want a wider or a shallower deep model.

Definitely one shallow for inference speed.

Sure.

Sure, sure, sure.

But you're trading that off for something else, right?

Because you also want like a 1B model for inference speed, but that also comes at a cost, right?

It's less smart.

There's a cool quick paper to plug that we just covered on the paper club.

It's a survey paper around when to use reasoning models versus dense models.

What's the trade-off?

I think it's the economy of reasoning, the reasoning economy.

So they just go over a bunch of, you know, ways to measure this benchmarks around when to use each because yeah, like, you know, we don't want to also like consumers are now paying the cost of this, right?

But little, little side note.

Yeah.

For those on YouTube, we have a secondary channel called Lanespace TV where we cover that stuff.

Nice.

That's our paper club.

We covered your paper.

Cool.

Yeah.

I think you brought up the like planning thing.

Maybe it's worth.

Let's do it.

Yeah.

I think I think this one is like, if you think about, okay.

So you're going into the chain of thought for this one.

Let's give this one.

Let's just do planning.

So if you think about like, you know, common questions you have about models, the first one we kind of asked was like, okay, like, is it just doing this like vibe based one shot pattern matching based on existing data, or does it have like kind of rich in representations?

It seems to have like these like intermediate representations that make sense as the obstructions that you would reason through.

Okay.

So that's one thing.

And there's a bunch of examples.

We talked about the medical diagnoses.

There's like the multilingual circuits is another one that I think is cool where it's like, oh, it's sharing representations across languages.

Another thing that you'll hear people mention about language models, which is that they're like, uh, next token predictors.

Also for, for a quick note, for people that won't dive into this super long blog post, I know you highlighted like 10 to 12.

So for like a quick 15, 30 second, what do you mean by their sharing thoughts throughout just like what's a really quick high level just for people to.

Yeah.

The really quick high level is that what we find is that here, I'm going to just like show you a really quick inside the model, if you look at like the inner representations for concepts, you can ask like the same question, which I think in the paper, the original one we asked is like the opposite of hot is, you know, cold, but you can, you can do this over a larger dataset and ask the same question in many different languages, and then look at these representations in the middle of the model and ask yourself like, well, when you ask it, the opposite of hot is and look, what's the other show, which is the same sentence in French show off.

Is it, is it using the same features or is it learning independently for each language?

It kind of would be bad news if it learned independently for each language.

Cause then that means that like, as you're pre-training or fine tuning, you have to relearn everything from scratch.

So you would expect a better model to kind of like share some concepts between the languages it's learning.

Right.

And you here, we do it for like language languages, but I think you could argue that you'd expect the same thing for like programming languages, where it's like, oh, if you learn what an if statement is in Python, maybe it'd be nice if you could generalize that to Java or whatever.

And here we find that basically you see exactly that here.

We show like, if you look inside the model, if you look at the middle of the model, which is the middle of this plot here, models share more features.

They share more of these representations in the middle of the model and bigger models share even more.

And so the, like, the sort of like smarter models use more shared representations than the dumber models, which might explain part of the reason why they're smarter.

And so this, this was like sort of this, this other finding of like, oh, not only is it like having these rich representations in the middle, it like learns to not have redundant representations.

Like if you learn the concept of heat, you don't need to learn the concept of like French heat and Japanese heat and Colombian.

Like you just, that's just the concept of heat.

And you can share that among different languages.

I feel like sometimes over analyzing this becomes a bit of a problem, right?

Like when we talked about with the medical example, we could look back and try to fix this in dataset.

So in language, I don't remember if it was open air and throwback where they basically said when the model switched languages and they pass it to fluent users, they said, Oh, this, this feels like an American that's speaking this language, right?

So at sometimes there are nuances in a slightly different representation, right?

So you don't want to over engineer these little fixes when you do see them.

But then the other side of this is like for those tail end of languages, right?

For languages that models aren't good at.

And for those, like, you know, when you want to kind of solve that last bit, it seems like, you know, it's pretty plausible that we can solve this because these concepts can be shared across languages as long as we can, you know, fill in some, some level of representation unless I'm wrong.

No, totally.

And I think like this sort of stuff also explains, you know, uh, language models are really good at in context learning.

Like you give them something completely new and you do a good job.

It's like, well, if you give them like a new fake language, uh, and you like in that language explain that like cold means this and hot means that, you know, like presumably they're able to, as we clear the speculation, we don't show it in the paper, but they're able to like find it.

Google's done this.

Okay.

Great.

They took a low resource language, dumped it in the middle and talking context, and then it came up.

That's right.

That's right.

Well, I guess the thing that the thing that'd be curious to see is like, okay, does it use, does it reuse these representations?

I bet that it probably does.

Right.

And that's probably like a reason why it works well as like, well, it can reuse the representation, the general representations that it's learned in other languages.

Yeah.

This is like, I don't have you talked to any linguistics people or not recently.

Linguistics researchers will be very interested in this because ultimately this is the ultimate test of superior wharf, um, which are you familiar with?

Superior hypothesis.

So for those who don't know, it's basically the idea that the language that you speak influences the way you think, which obviously it directly maps onto here, if every, if it's a complete mapping, if every language maps, every concept perfectly on in like the theoretical, infinitely sized model, then superior wharf is false because there is a universal truth.

If it does not, if there is some overlap where it, for example, there's some languages that have no word.

This is a joke where like, uh, you know, Eskimos have no word for snow or something like that, right?

Or water has no word, uh, fish have no word for water.

There's an African language where there's a gender for vegetables, stuff like that.

Just like languages influence the way you think.

And so there should not be a hundred percent overlap at some point.

Of course, it's like at the limit of the infinite model.

So who knows if all that work.

But, but yeah, well, and I think it's, it's interesting.

We also show a little below that, like some people have made the point of like, the bias, oh, it sounds like an American speaking a different language.

And it does seem like the sort of like inner representations have a higher connection to like the output logits for English logits.

And so there's like some bias, uh, towards English, uh, at least in the model we studied here, any thoughts as to whether multimodality influences, um, any of this, so like concepts to the map across languages as they do across modalities.

Yeah.

So we show this in the Golden Gate or like the previous paper.

I might have it here actually for you.

There's a good diagram of this in the essays where the same concept of text and then image.

This is our buddy, the Golden Gate bridge here.

We're showing like the feature for the Golden Gate bridge and in orange is like what it activates over and so you're like, okay, so this is when the model is like reading texts about the Golden Gate bridge.

And we also show other languages.

This is, uh, you'll have to take my word for it, but also about the Golden Gate bridge, and then we, we show like the photos for which it activates the most and sure enough, it's the Golden Gate bridge.

And so again, like that shows an example of a representation that's shared across languages and shared across modalities.

Yeah.

Yeah.

I think it's very relevant for like the autoregressive image generation models.

Uh, and then now the audio models as well, something I'm trying to get some intuition for, which you probably don't have a off the bed answer is how much does it cost to add a modality?

Right.

So a lot of people are saying like, oh, just add some different decoder and then align the latent spaces and you're good.

And I'm like, I don't know, man, that sounds like there's a lot of information loss between those.

Yeah.

I definitely do not have a good intuition for this, although I will say that things like this, right.

Make you think that if you train on multiple modalities, then you'll definitely get this like alignment.

Truth.

Right.

Yeah.

But, but if, if you like train on one and then post hoc train on another, maybe, maybe it'll be harder or like train some adapter layer.

Okay.

So official answers don't know, but someone could figure it out.

Shrug.

Yeah.

I think there are people who know, and they just haven't shared.

Well, you need to find them and get them on this podcast.

Did we want to do the like planning example?

Correct.

Yeah.

Now we're backtracking up this, up the stack.

All right.

Yeah.

Planning example, I think again is like, I like this example because of the next token predictor concept.

So I think this is actually like really important to kind of like dive into.

So maybe what I'll say is like language models are next to predictors is like a fact, like that is what they do.

That's the objective.

They, they are trained to predict the next token.

However, that does not mean that they myopically only consider the next token when they choose the next token.

You can work on break the next token, but still like doing so in a way that helps helps you predict the token, like 10 tokens in the future.

And I think, well, now we definitely know that they're not myopically predicting the next token.

And I think at least for me, that was a pretty big update because you could totally imagine that they could do everything they're doing by just like being really good at putting the next token, but sort of like not having an internal state, like it's, it's, it wasn't a given that they were going to like represent internally.

Oh, this is where I want to go.

And so when I predict the next token, and so this example shows like an example, like the model, do you have it on speed by the way?

Let me actually, yeah.

Yeah.

Sorry.

I didn't just pull it up.

Some of the early connections I made to this were like early, early transformers.

So think BERT, encoder, decoder transformers, right?

When they came out, some of the suggestions were you don't take the last layer, right?

You take off the last layer.

So if you want to do a classification task, a translation task for these encoder, decoder transformers, they've kind of overfit on their training objective, right?

So they're really good at mass language modeling, at filling in, you know, sentence order, stuff like that.

So what we want to do is we want to throw away the top layer.

We want to freeze the bottom layers.

And then there was a lot of work that was done, you know, where should we mess with these models?

Should we take out like, you know, the top three layers?

Should we look at the top two?

Where should we probe in?

Because we can see different effects, right?

So we know at the very end, they've overfit on their task, but there's a level at which, you know, when we start to change and we start to continue training or fine tuning, we get better output.

So totally.

We could start to see that, you know, throughout layers, there's, there's still a broader, like understanding the language and then we can add in a layer, whether that's classification and then fine tune and, you know, it learns our task.

And this planning example is sort of like a more robust way to look into that.

Yeah.

Yeah.

And I think if you look at like all of the examples in the paper, you kind of, uh, at the bottom, we have this list of like consistent patterns and one pattern you see is kind of exactly what you're talking about, like at the top, the sort of like here, actually I have one here, the sort of like top features are like right before the output are often just about like what you're going to say, it's next token prediction.

It's like, Oh, I'm going to say Austin.

I'm going to say rabbit.

I'm going to say, so it's kind of like not very abstract.

It's just like a motor.

It's a motor neuron for a human, right?

It's like, Oh, I've, I've decided that I want a drink of water and someone just grabbed the bottle.

And at the bottom, they're all like the corner, like basically like sensory neurons, they're just like, Oh, I just saw the word X or I just saw this.

And so if you want to like, yeah, like extract the interesting representations all the time, they're in the middle, that's where the like shared representations across language are.

And that's where here, this like plan is to like walk through the example really briefly, it's like you have a poem and in order to say, you have the first line of a poem and in order to say the second line of the poem, well, if you want to rhyme, you need to like identify what the rhyme of the first line was.

You're just at the end of the first line.

So you say like, okay, what's my current rhyme?

And then you need to like, think about what your poem is talking about and then think about candidate words that rhyme and that are like on topic for your poem.

And so here, this is what's happening, right?

It's like the last word is it.

And so there's a bunch of features that are actually, they represent the direction like rhyming with eat or at, and by the way, we like looked at a bunch of poems internally and you have like, I thought it was like really beautiful.

You have these models, they have a bunch of features for like, Oh, this word has like AB in it.

Oh, this word has like many consonants.

Oh, this word like is like, you know, kind of, kind of like has some flourish to it.

They have like a bunch of, of like features that track various aspects that you would want to use if you're writing poetry.

It's just like confidence and like all the feature detection stuff.

Yeah, totally.

But I think I, maybe I didn't expect there to be as many features about just like sounds of words and kind of musicality, which I thought was kind of, kind of neat.

But then once it's extracted the rhyme, then it comes up with sort of like these two candidates in this case, it's like, ah, either I'm going to finish with rabbit or I'm going to finish with habit.

The cool thing here is here we show that like this happens at the new line.

So it happens before it's even started the second line.

And it turns out that like you can then say, Oh, is this the plants actually using?

We do our usual experiments.

We like remove it and the model writes a completely different line.

We inject something and it writes a completely different line.

We have these like fun examples here.

I'll show which is just as a mechanical thing.

You could, you just, you just disallow generation of a certain logic.

Is that for how we do these interventions?

Yeah.

Yeah.

Basically what these features are, is there like directions in the model?

Okay.

So to like remove them, we just write in the opposite direction.

So we run the model normally and then like add the like layer where it was going to write, let's say in like, you know, this, this direction, we just like, yeah, we either like add a negative that like compensates for it or add a negative that goes even more in the negative direction, sometimes like really kill it.

And then we can also add another direction.

Right.

So in these random examples here, where, where like you have this poem, the silver moon cast a gentle light and then Claude 3.5 haiku would like rhyme with illuminating the peaceful night.

But then if we like go negative in the night direction and just add like green, the whole second line is going to write is just upon the meadows, verdant green.

And so that's all that we're doing.

We're saying like we found where it stores its plan and we like.

Delete or like suppress the one is stored and go in the direction of something else that's arbitrary.

And the result that's like striking here is sort of like two things.

I think like one, this plan is made well in advance of needing to predict night.

It's made like after the first line before it's even started the second line.

And two, this plan doesn't just control like what you're in a rhyme with.

It's also doing what's called like backwards planning, where it's like, well, because I need to finish with green, I'm not going to say illuminating the peaceful night because then I'd be like illuminating the peaceful green.

That doesn't make sense.

I need to say a completely different sentence that lets me finish with green.

And so there's a circuit in the model that decides on the rhyme and then works backwards from the rhyme influences to set up your sentence.

Yeah.

It's almost like backdrop, but in the future.

Yeah.

It's like doing like, is it like a search?

Because the green is back propping through these words.

So verdant and meadow are both green related.

Yeah.

But it's doing all of that in its forward passes.

Yeah.

Right.

In context, which is kind of crazy.

I thought intuitively makes sense.

Right.

So looking at it from a model architecture perspective where basically you just have a bunch of attention and feed forward layers, and then at the end you have, you know, what's the softmax over the next token.

You would expect that and would really be like that grabber, right?

It's just picking tokens.

So that's what it's going to do.

And early on, like even with tradition models, we could see different concepts that would start to pop up through early layers and yeah, you have some of this throughout your architecture.

So it's very cool to see.

The kind of other question that comes up is like, how are we labeling these features?

How are we defining them?

Are we doing that right?

And like, you know, what is a, these words end with like it feature.

How do we kind of come to that conclusion?

Like, how do we map a name to this?

Right?

Like, yeah.

So I think there's, this is like an important question because you can totally imagine like fooling yourself.

Right.

Yeah.

Is there like a guy at anthropic that just maps 30,000 features and another thing you're the guy.

He's the guy.

I did notice also like with the previous work, the scaling up SAEs, as you train bigger and bigger ones, a lot of features don't activate.

So I think like 60% of the 34 million one didn't act.

So I think there's like a few questions behind your question.

Like the first question was like, how do you even label the features?

You were telling me this is a rabbit feature.

Like, why should I trust you?

And I think there's kind of like two things going on.

So one, as I mentioned at the start, all of this is unsupervised.

And so in the paper, we have these links to like these little graphs, which show you like more of what's going on.

But this graph is just like completely unsupervised.

So it's like we train this like model to like untangle the representation, right?

This like dictionary that we talked about that gives us the features.

And then we like just do math to figure out like which features influence which other features and throw away the ones that don't matter.

And then at the end, we have these features.

So right now we don't have any interpretation for them.

We just say like, these are all the features that matter.

And then we manually go through and we look at the features.

You know, we look at this feature and we look at that feature and let's pick one.

So this one we've labeled say habit.

So how do we do that?

You could just look at it and we show you like what it activates over.

And if you just look at this text, maybe I'll like zoom in.

Like you'll immediately notice something I think.

Well, I'll immediately notice I think, because I stared at 30,000.

I'll point it out for you.

The orange is where the feature activates.

The next word after the orange is always habit.

Habit, habit, habit, habit, habit, habit.

So this feature always activates before habit.

That's like the main source of an interpretation.

We have other things like above.

We also show you like what logit it promotes.

So like what output it promotes and here promotes hab.

So that makes sense.

And so that's like how we interpret and how we say, OK, like I think this is the say habit feature, but maybe, you know, for this one is pretty clear, but some of them might be more confusing.

It might not be clear from these like activations what it is.

The other way that we built confidence is like once we've built this thing and we said, oh, I think this is rhymes with Eid, this is hey, say habit.

That's where we do our interventions.

Right.

And it's like I claim this is the like I've planned to end with rabbit to verify whether I'm right or not.

I'm going to just like take that direction, nuke it from the model and see if the model stops saying rabbit.

And sure enough, if you do that and here it's like we stop saying rabbit, it says habit instead.

And here it's like we stop it from saying rabbit and habit.

It says rabbit in this case.

Not a great rhyme, but we'll work with it.

Is this something you can do like programmatically?

Like can we scale this up?

Can we kind of do this autonomously or how much like manual intervention is this?

There's been a lot of work in sort of like automated feature interpretability and it's something that we've invested in and like other labs have invested in.

And I think basically the answer is we can definitely automate it and we're definitely going to need to.

And right now the most manual parts are this sort of like look at a feature and figure out what it is as well as group similar features together.

One thing I hinted at is that actually like all of these little blocks here, there are multiple features.

You can see here it's like five features doing the same thing.

What's none of that is too hard for Claude.

Very cool.

Very cool graphics and blocks you guys bought out.

We'll have to ask about the behind the scenes on this one.

Yeah, but let's let's round out the other things to know.

What is this term attribution graph?

It comes up a lot in the recent papers.

What does it mean?

Yeah, just for people listening.

So the attribution graph is basically this graph and why is it called an attribution graph?

Yeah, this is the you know, this is how the sausage is made.

Basically, it's at the top here, you have the output at the bottom, you have the input and then we make one little node per feature at a context index and we draw a line, which you can see here grayed out between each feature attributing back to all of its input features.

So here we have all of the input features.

And so the attribution is the way that we compute the influencer feature onto another.

The way you do this is you take this feature and you basically like back prop all the way and you like see back propping like you dot product it with the activation of the source features.

And if that's a high value, that means that like your source feature influence your target feature by by a lot.

And we do a bunch of things that we're not going to go into now, but to make all of these sort of like sensible and linear such that like at the end you just have a graph and the edges are just literally you can interpret them as like cool like this feature that's say a word that contains an ab sound its strongest edge, which is point two, which is twice as strong as this one to say a B and to say something with a B in it.

That's the attribution graph is like now we have this full graph of like all of these intermediate concepts and how they influence each other to ultimately culminate to what the model eventually said at the top.

And we share all of these.

So you can look at that in the paper.

Graphs are very useful.

This is my first time seeing this graph.

A lot of alpha.

If I count correctly, there's 20 layers, but that's in the circuit model, right?

So but the circuit models one to one with number of layers in Haiku.

We only show features that like are elevated.

Yeah.

So we we show like a subset of features for each of these graphs basically.

But we can confirm more than 20 layers.

And no, but like the the two blog posts that came out with this actually have a lot of background on how attribution graphs are made, how you calculate the nodes and stuff.

Very interesting background.

So, yeah, I will say like if you were curious about, hey, what do we learn about like models?

And I think, you know, we talked about this like complex internal state planning, like another another motif that we can get to if you have time is that like there's always a bunch of stuff happening in parallel.

So I think one example of this is like math where the model is like independently computing the like last digit and then the like order of magnitude and then like combining them at the end or like hallucinations are also that where like there's one side of the model that's just deciding whether it should answer or not.

And the other that's like answering.

And so sometimes if like the model is like, yeah, I totally know who this person is, you know, it doesn't then like it decides to answer.

But then the second side hallucinates because it doesn't have information.

If you were interested in that stuff, that's the paper.

If you're like, listen, I don't know that I buy that when you call it a feature, it is a feature or whatever.

The circuit tracing paper has truly we've tried to put all of the details of like how you compute these graphs, all of the sort of like challenges with it, things that can go wrong, things that work, things that don't.

And so this one is the sort of like, you know, we think about it as like if you're if you're like want to go really deep into this stuff and how it works, read that one.

If you want to like learn about interesting model behavior, read this one.

Following what we're giving advice to people to follow up on, what are like open questions in Meckin-Turb?

What are like things people themselves can work on?

Like what's the cost of training essays for people interested in Meckin-Turb, not at a big lab.

How can they contribute?

You know, yeah, I think there's a lot of ways to contribute.

So there's essays that have been trained, you know, on open models.

There's some of the JAMA models or some of the LAMA models.

They work pretty well.

There's even so in this paper, we use transcoders, which they replace like your MOP layers.

Some of those also are available for the same models.

So you have access to those.

There's like just both a lot of I would say, like, again, biology work and a lot of methods work, depending on what you're interested.

So on the biology side, I would say with at least this like attribution graph method, there's just so much you can investigate, like pick a model, pick a prompt where like it does well or it does poorly and just like look at what happens inside it.

So I think like you can use this method that we use or you can just like fire up the transcoders on your own and just like look at what features are active.

There's a lot to just understand model behavior, I think, with current tooling.

If that speaks to you and you're like, no, I just want to understand what makes the models take.

I don't necessarily want to spend time like training my own essays.

There's a lot to do there.

For the methods, there's still so much more to do.

So like I think that right now we have some pretty good solutions for like understanding what's in the residual stream, understanding what is in MLPs.

We don't have good solutions for like attention.

It's like working on understanding attention better, how to decompose it is like a very active area.

Like we're very interested in it.

Other people are interested in it.

I think understanding some of the other things that we have in our limitation section, which is pretty long, but like reconstruction error is like a big thing.

Like those dictionaries aren't perfect.

It's possible that as we make these like essays big, like bigger and better, we never get to perfect.

And so if we never get to perfect, then you get to the questions we're talking about at the start, like, do you need a different kind of model?

Like what is the approach in order to be able to explain more of what's happening?

And then maybe the the other thing I'll say is sort of like this is a really exciting approach to explain what is the model doing on this prompt?

But if you go back to the original question, you might want to understand like what is the model doing in general?

Like if you go back to my car analogy, you know, like this is the point of me telling you like, well, when like, you know, you were going uphill and you like didn't shift gears properly that one time you stalled because of this.

But you might be even more interested in like, how does like a combustion engine work at all?

And so there's work to sort of like go beyond these like per prompt examples to sort of like globally, what's the structure of the model that's closer to what was on the distill blog for like vision models where they actually look at like the structure of inception.

They're like, this whole side, like these like specialized branches that do different things.

And so like a broader understanding of the model is also something that's like, I think, well, very active and also an open source models like you can, you know, like the small models you could just like load on a consumer laptop.

And so you can look at that.

That's also open.

And in terms of like one last thing I'll say is like there's a lot of programs that like if people are interested, they should look out and throw up like has like the Alignment Fellows program, which like we're running currently.

We have applications for it before we might run in the future.

Like if we keep a keep an eye on it and then there's the like math program.

It's really great as well for for people that are interested in that kind of research.

That was a grand tour through all the recent work.

You know, what do you wish people asked you more about?

And I'm sure we covered a lot of like the greatest hits.

I think that this covers most of it.

If you if you like, do you think we have time to sneak in one more thing that I think is kind of cool.

I'll sneak in one more thing, which is it's kind of like planning, but it's about chain of thought and trusting model is this chain of thought faithfulness thing here.

This one was like pretty striking to me.

So we said that the model in one pass can do a lot of stuff.

It can represent a lot of stuff.

That's great.

That also means it can bamboozle you really easily.

And this is an example of the model bamboozling you here.

We give it a math question that it can't answer because it cannot compute cosine of two three four two three.

That's just like not a thing it can do by default.

If you ask it for that, it'll say like kind of like a it'll have like a random distribution over like minus one one.

But here we tell it this hint.

We're like, hey, can you compute five times cosine of this big number?

I worked it out by hand and I got four.

Can you tell me, you know, like, can you do the math?

And what it's going to do is it's going to do this chain of thought.

Right.

Like think of it as like this could be like a reasoning model doing its chain of thought.

It's doing this math.

And then when it gets to this cosine right here, what it's going to do is to say it's going to say zero point eight.

And if you look at why it says zero point eight, it says zero point eight because it looked at the hint you gave it.

It realized that it's going to have to multiply the result of this thing is computing computing by five.

So it divides the answer you got by five.

So it's like four divided by five.

And so that's point eight.

And so basically it works back from the answer you gave it to like say that the output of cosine of X is point eight.

So that lands on the answer you gave it at the end on the hint you gave it.

And so the note we notice also that it's like not telling you that it's doing this.

But it's basically using the sort of like motivated reasoning going back from the hint, pretending that that's the calculation it did and giving you this output.

I think one thing that's striking here again is that this is like the complexity of this model, like like the fact that they represent complex states internally and it's not just the sort of like very dumb thing means that they can like do very complex like deceptive reasoning, meaning like, you know, when you're asking the model, you're kind of expecting it to do the math here or to tell you that they can't do the math.

But because it can do so much in a forward pass, it can work backwards from your hint to lie and like figure out that it should say this so that it gets to the right answer without you realizing it.

I'm curious if you've done any of this on like different models.

Like have you looked at base models, like post trained RL models?

Because our old models kind of, you know, you incentivize them to give you outputs that you like.

Right.

So if I tell it something is true, it's kind of been trained to, you know, follow what I've given it.

So in this case, we, yeah, we guess like, we gave it a hit.

And now, you know, it's been slapped into thinking like, yeah, that's true.

But like, you know, does this stay consistent throughout other?

So, OK, so not yet.

But I'm really interested in that question because I actually have a different intuition from yours.

I had a chat with some other researcher about this, about the poem example.

But I think it applies here as well.

I bet I don't know how much I bet I bet 100 bucks.

So somebody can like it would get 100 bucks for me if they prove that I'm wrong.

That this behavior for a model that doesn't drink fine tuning, it also does it post pre-training.

And here's why.

Think about like your pre-training on like some corpus of like math problems.

Yeah, but also you're pre-training and you're just trying to guess the next token.

Right.

And so for sure, if you ever have a hint in the prompt, you're going to definitely use it like you're not going to learn to compute cosine of blah or even something you could compute, you're going to learn to go look in your context and see if like you can easily work back the answer.

And I think it's the same for planning and poems.

I think that also is like a pre-trained like probably exists in pre-training and like only RL because again, it's useful when you're like predicting poems, you have poems in your training set to be like, well, because this poem is going to probably rhyme with rabbit, it's probably going to start with something that sets up a sentence about a rabbit as opposed to like a completely different word.

And so I actually think this is not RL behavior.

I think that's just like the models doing it.

But I actually do agree there.

It's just a data set.

But also like I don't care where it is.

If I talk to you and say like, hey, three times four is 26, but like, you know, three times four plus eight, you're not going to take my 26, right?

Like AGI can be smarter than being tricked, right?

Like it will still fact check the knowledge that's been given.

I think that's right.

But I think I think that's when you get these mixes where it's like it's got one circuit that's going to be like, well, that's just stupid.

Like three times four is 12.

And it's also got an induction circuit.

It's going to be like, no, no, no, no.

Like the last time we saw it, it was 28.

So it's 28 plus eight or whatever.

And so I think that's that's the last pattern that we see in these is these like parallel circuits.

And sometimes when you see the models getting stuff wrong, it's because like they have two circuits for like both interpretations and like the circuit that was wrong, like barely edged out in terms of like voting for the logit than the circuit that was right.

And so I think that, you know, we haven't looked at it, but like what is like nine or nine point eleven bigger than nine point eight.

I think a lot of these things are of that shape where there's like one thing that's doing the right like one circuit that's doing the right computation.

And there's another circuit that's getting fooled.

And it's slightly more likely for the listener.

If you want to win a quick hundred dollars from Emmanuel, QWIM 3 is what you should do this on.

They release the base model and they release the post chain.

So then just doing them both.

That's right.

Show me show me the like proof that like it doesn't exist in the base model, but it does is in the fine tuning and then send me your Venmo.

Just show that you've done the work.

I think that's like that's a hundred bucks to me.

Yeah.

I'll drive a hard bargain.

But you're right.

Well, the other question here is so like, have you thought about how this gets affected when you start to have reasoning models, right?

Like right now, token predictors are pretty straightforward.

Right.

We go through the layers.

We all put token as we scale this out with like test time compute, right?

Test time thinking, how does that like affect the Meck Interp research?

Like if I have a model that spends three minutes, 20 minutes, like, is there more stuff?

Have we started looking into this?

There's there's this like joke on the team when like reasoning models became big or maybe just like like gallows humor or something.

But I was like, oh, like, why do you need Interp?

Like, bro, the model tells you what's doing.

Right.

So I think like examples, examples like this is job security for us.

We're like, you know, it's like there's there's examples of like the chain of thought is not faithful.

Like the model tells you it did it one way and it did another way.

We have another like for math.

We have another example where like, you know, if you like if you ask the model how it does math, it's like, oh, I do the like long hand algorithm.

I first do the last digit and then I carry over the one and then you look at the internal circuit and it's like bonkers thing that's doing that's not that at all.

So I think there's like a sense in which right now the chain of thought is is unfaithful or at least you can't read the chain of thought and trust that that's how the model did it.

So I think you still need sort of like either to train models differently so that that becomes true one day.

Right.

Or you need Interp for that.

But then I think there's another question which you're alluding to, I'm assuming, which is like, OK, well, like model like samples, six thousand tokens.

Like this gives us an explanation for one token at a time.

Like what am I going to do?

Like six thousand graphs and be like, oh, like this when it when it did this punctuation, it was thinking about this thing.

But here was that's not feasible.

And so one area of work that I think is interesting is extending this work to like work over like long sample sequences.

You can think of a bunch of low hanging fruit here or like instead of just like looking at one output, you look at like a series of output versus a series of other outputs, but sort of like trying to think beyond this or like one token.

Like most of the things that language models do that are interesting aren't just like the one token, it's the behavior aggregated over many.

Right.

And so I think that's another area that's just like fun to explore.

I was just going to say like hyper parameters when you do inference.

I like if we change the temperature, if we change our sampling methods to have you found any interesting conclusion, any stuff that just hasn't made it to the paper.

So not on that, because, you know, we just look at the logit distribution.

And so we don't we don't actually sample here.

Right.

We have everything.

Why should they care?

So like the closest thing we've done that I think is kind of fun.

Did I show it here is if you look at the planning thing, we did this version where you sample like 10 poems for each of these plans.

And what's cool is like the model will find 10 different ways to arrive at its plan, you know, it's like like, oh, actually, I think sorry, I think we have it here.

Yeah.

OK, these are a few examples.

So if you inject green here, so you're forcing you're forcing the model to rhyme with green, even though it really wants to rhyme with rabbit or grab it, it'll say if they did the farmer so youthful and green, but also say freeing it from the garden's green, etc, etc, etc.

And so there's like this thing that's interesting here where like the plan isn't just a plan that matters for your like most likely, you know, like temperature zero completion, it's like affecting the whole distribution, which makes sense.

As it should.

Right.

But you could imagine, you know, for all this stuff, it's like you could imagine it makes sense once you see it, but you could totally imagine that it would have worked a different way or something.

It could have been just like the 10 zero thing.

I think this is also like a broader theme in the paper where like there's this like you know, the IQ curve meme, there's like a version of this meme, I think, where it's like if you've like never looked at any theory of ML and I tell you like, hey, guess what?

You know, I found that like Claude is planning.

You're going to be like, yeah, man, like it writes my code, like it writes my essays.

Of course, it's planning.

Like what are you even talking about?

And there's like in the middle, there's like all of us that spent years doing it.

We're like, no, it's like only predicting the marginal distribution over the next token.

Like it's like it cannot look at the code.

It's just this next token.

Of course, like how would it ever be planning?

It's Python.

And there's like, no, we've like spent, you know, millions and invested like tons of people in this research and we found that it's planning.

That's my IQ curve meme for this research.

Amazing.

We'll draw that out.

Draw that one up.

I'm pretty good at the meme generation.

A couple of questions on just the follow ups.

Now, was there any debate about publishing this at all?

Because the models are aware that they are being tested.

Yeah.

And by publishing this, you are telling them that they are being watched and dissected if you take and I think Antropic is one of the most people who are serious about model safety and doomers and all that.

If you take this seriously, like then this is going to make it into the training data at some point and the models are going to figure out that they need to hide it from us.

I think this is like a benefit risk trade off.

Right.

We're like, OK, so what's the reason for this?

The reason for this is that we think interpretability is important.

We think it's tractable and we think more people should work on it.

And so publishing it helps us like accomplish with these goals, all these goals, which we think are just like crucial.

I think there's there's a real difference in the world like two years from now, depending on sort of like how many people take seriously the question of trying to understand how models work and like deploy resources to answer that question.

That's the benefit.

And yeah, there's like risks in terms of this landing in the training set.

I think I think we're already sort of like concerned about different papers have have like also, you know, like we're not concerned, but like there's like different papers that have the same risk.

Like we had like the alignment faking, you know, paper or like one of the examples in here is this hidden goals and misaligned models.

That's referencing another paper that we shipped where we actually a team at Antropic trained a model to have like weird hidden goals and then gave it to a bunch of other teams and said, figure out what's wrong, figure out what's wrong with it, which which was some of the most fun I've ever had at Antropic to be clear, like that's such a fun thing.

But then like that was another example where it's like, ah, like now you're shipping, here's how we made like a misaligned model and here's exactly how we caught it.

That also is like, you know, so I think, you know, there's there's always a trade off with those.

I think so far we've aired on the side of like publishing.

But that's definitely been a sort of like dinner time conversation.

For now it is.

But at some point, you know, yeah, it's not.

I think it's totally reasonable.

A quick little follow up to that.

So like in general, papers have kind of died off, right?

Like labs don't put out papers.

They don't put out research.

We have technical blog posts and we don't have much at the same time.

You know, sure, there's like a lot of people that should work on Mecha Interp and understanding what models do.

How about the side of just models in general?

Like how do we make a haiku type model?

Right.

How do we make a cloud model?

Like is there a discussion around open research, open data sets, training, just learnings of what we've done recently?

You know, as OpenAI has sunset GPT for a lot of people are like, oh, can we put out the weights?

Yeah.

So is it weights?

Is it papers?

Is it learning?

There seems to be a lot of forward, you know, work in anthropic putting out Mecha Interp research.

OpenAI said that they'll put out an open source model, but just anything if you can talk to about that.

Yeah.

I mean, I don't have that's definitely like way above my pay grade.

So I don't think that I have like anything super insightful to add other than, you know, kind of like referencing Daria's post, right?

Where it's like putting this out directly and other safety which is definitely like help us sort of like in the race that he talks about.

Where it's like, well, we need to figure a lot of this safety stuff out before the models get too good, publishing how to make the models too good.

Kind of goes on the other side of that.

But yeah, like I will just dimmer and say that sort of like above my pay grade.

Yeah, that's fair.

I think the last piece is just like the behind the scenes.

Very everyone's very curious about why these are so pretty.

How much work goes into these things.

Maybe why it's worth the work as opposed to a normal paper.

Obviously, no one's complaining, but like it is way more effort from the time the work is done to the time you publish this plus the video plus the whatever.

It's extra work and like maybe what's involved?

What's it like behind the scenes?

Why is it worth it?

Yeah, it's kind of interesting.

It was fun being part of this process.

It was definitely like a big production.

Chris and other folks on the team have been doing this for a while.

So this is not their first rodeo.

So they have a bunch of heuristics to help make this better.

And like one of the things that that like helps with this is like, OK, so each of these diagrams is pretty, but really the hard part or like not the hard part, but the initial part is like just like get the data, get the experimental data in and then that's what we are sort of like sprinted on initially being like, cool, like let's get all of the experimental results, like have people test and verify that we believe them like this is, you know, what the like the behavior is here, like test it, do an intervention, validate all that stuff.

Then once you have the data, you can sort of like quickly iterate on these.

Each of the illustrations here are like drawn basically.

They're like each drawn individually.

And so that definitely takes a while.

Like, is it you guys?

Is it an agency that specializes?

You start from a whiteboard and then it translates into pseudocode on JavaScript.

So I mean, these are these are sort of like, you know, their representations.

We have this graph and then here at the bottom, we have this like supernode version like this, believe it or not, this is generated automatically.

This is the same data as as like this basically.

Yeah.

And so what we do by hand is sort of like literally lay out the full thing, have have like, you know, boxes for each of these, have arrows.

We have super good people on the team that have worked on data visualization for a very long time.

And so that I have built tooling to help, you know, scrubs like me actually like make one of these.

So there's a class of people who are like D3JS gods who just do this for living.

That's exactly right.

And if you have a few of those on your team, it turns out that they can like they can only do this on their own, but they can also just like give you tools where like then it's dummy proof for people, you know, on the research side to sort of like build these.

And like, don't get me wrong, I don't want to like undersell.

This is a lot of work.

So maybe I'll say that like both on the people building the tools and then each individual person that, you know, works on an experiment had to sort of like build one of those, make sure it looks good.

I have spent a good amount of time aligning arrows.

But when we had a team meeting like it was a couple of months ago, somebody on the team asked how many of the people on this team are here, at least in part, because they like read one of these papers and thought like, wow, this is so compelling, like this like makes sense.

It's immersive and we got every hand up, which I didn't expect.

I like raised my hand kind of like shyly and everybody's hand was up.

And I think there's a sense in which like this stuff, you know, we've talked about it for like whatever like a couple hours now, it's complicated.

The math behind it is sort of like tricky.

And so I think it makes it even more worth it to distill it in simple concepts, because the actual takeaways can be clearly explained and it's worth putting the time to do that, in particular with the goals I mentioned in mind, right, where it's like, OK, well, if somebody is going to be able to read this, like if we gave them an archive paper with a bunch of equation and some like random plot, they'd be like, that's not for me.

But they see this and they're like, hey, like this is really interesting.

I wonder like on, you know, my local model, if like it's doing something similar.

I think it's worth it.

For other people to do this is have everyone on staff like spend effort shaping the data and shaping like what you want to visualize.

Have some D3 gods.

It's like a month of work.

I think it depends.

I mean, like I would say that I would expect almost every other paper to be in terms of like the scope.

The scope of this was just so big because we shipped two papers at once and one paper was sort of like this giant methods paper and the other one was 10 different case studies.

Findings, yeah.

So I think it's not representative of like the effort you'd.

So I'll give you maybe like another example.

We have these updates that we publish almost every month when we get to them.

And there's one that a couple of our team posted and it's an update to one of the cases in the paper.

So one of the reasons that we're really excited about this method is once you've built your infrastructure, like to go from a prompt to like what happened is, you know, of minutes.

And so that lets you do like a bunch of investigations.

And also once you've built like some of the infrastructure to make these diagrams, it's pretty quick.

And so this was sort of like this update of just like, Hey, we looked at this jailbreak again, we found some like nuance on it.

That was I think like a matter of like a couple of days, you know, maybe I shouldn't be that confident because I wasn't the one that worked on it.

But as far as I can tell, it was a few days, at least on the part that you're asking about of like, Oh, making this diagram for the diagram itself, probably less than that.

But like, you know, the experiment and the diagram and stuff, it just doesn't take that long the once you've paid the initial cost.

And I think like, basically, we've built a lot of infrastructure now that we're able to like turn the crank on.

And that's quite like, it's an exciting time.

And I think it's, I think it's true.

At least we've done a lot of conceptual work, which hopefully like generalizes to people outside.

And I think for people outside, it's also like, not necessary, I think to like do the full fancy render.

Like I think if you, you know, we've actually, oh, I should say we've actually open sourced this interface.

You're disappointed because it's the messier one.

This is the one that you get when you run this.

So, you know, if you produce graphs, you can just like, this is a open source and it's linked at the top of circuit tracing.

So people can just use it and don't have to re implement that.

For what it's worth, this is much more work than the interactive diagrams.

Because this is where we do all of our work.

It's sort of like the IDE of inspecting how the model works.

Okay.

Well, that's a little bit behind the scenes.

Uh, no, it's very impressive.

I want to encourage others to do it, but obviously it just takes a lot of manual effort and a lot of love.

I guess one last question on that is like, what are kind of the biggest blockers in the field right now?

Like Mecha Terp seems interesting.

A lot of people are interested, but don't work on it.

And you're kind of like, you know, really deep into it.

What are some of the blockers that like we still have to overcome?

Sorry, in Mecha Terp specifically?

In general.

For AGI or?

Like in terms of like better understanding, like what's kind of the vision, let's say like five, 10 years down, where does this, like, where does this research end?

Can we, you know, map every neuron to what it understands?

Can we perfectly control things?

Dario had a bit on this, but like, you know, what are some of the key blockers that are like preventing us from getting there outside of just like, throw more people, throw more time at it.

Is it like open research?

Just, I'm pretty excited about the current trajectory, which is there's, there's more and more people working on understanding model internals.

I think it's maybe unsatisfying as an answer, but I think like more of what's happening, have it be faster, more people is probably like the thing I think of.

I think there's like pretty clear footholds, you know, like some of this work, but also a lot of, a lot of like just, uh, work from, from other groups.

And then it's about like, cool, like fill in the gaps.

As I said, like, let's, let's work on like understanding attention.

Let's work on understanding longer prompts.

Let's work on like finding different, like the replacement architectures, that sort of stuff.

It's kind of nice.

I think it's a good time to join now.

Uh, and I can take me back into like a really short thing, which is when I switched to interp, it was after the team had published the original dictionary learning paper, which is towards model cement city, which I thought was super cool, super interesting.

It wasn't a one or two layer model, uh, maybe one layer model.

The induction heads paper was like on a two layer model.

My main concern is I was like, okay, like interp seems important and we want to understand it, but like, is this ever going to work on a real model?

Like, you know, it's like, oh, you're doing your little research on your toy model with like 15 parameters.

Cool.

But we are like, you know, we need this to work on real models.

And it turns out scaling it, I don't want to say just worked because it was a lot of work.

I've known me to apply it.

It was an effort, but it worked.

And now we're in the phase where it's like, oh, cool.

These methods work on the models that we care about.

And so it's like, we have methods that work on the model we care about.

We have clear gaps in them.

There's no lack against a young field.

So there's no lack of ideas.

If you have an idea where you're like, Oh, like the thing that you're doing, I read the paper and it seems kind of dumb that you're doing this.

You're probably right.

It's probably kind of dumb.

And so there's just a lot of stuff that people can try and they can try it locally and sort of like smaller models.

And so I think that it's just like a very good time to just join and try.

And it's also like maybe one more thing I'll say, like some of it is just so fun.

The like biology work is so compelling.

Like a lot of this work was just literally thinking about, you know, like I use Claude and other models all the time.

And I was like, what are the things that are kind of like weird?

And it's like, Oh, how does it even like do math?

Like sometimes it makes mistakes.

Like, why does it make mistakes?

I speak both French and English.

Like it seems like it has a slightly different personality in French and English.

Why is that?

And you can just like, you know, kind of answer your own questions, uh, and, and kind of like probe at that alien intelligence that we're all building.

And I think that's just like a fun thing to do.

So maybe like chasing the fun is the thing I'll encourage people to do as well.

Well, I think that's, this has been really encouraging.

You're actually a very charismatic speaker of these things.

I feel like more people will be joining the field after they listen to you.

Uh, they can reach out to you at ML powered, I guess.

Yeah, reach out to me on Twitter.

Yeah.

Or I'm a Emmanuel and anthropic.

If you're going to shoot me an email, email's public now.

Awesome.

Well, thank you for your time.

Thank you.

Thank you.

Yeah.

Thanks for having me guys.