Dan Braun

Lead engineer at Apollo Research

Wiki Contributions

Comments

Dan BraunΩ230

Every SAE in the paper is hosted on wandb, only some are hosted on huggingface, so I suggest loading them from wandb for now.  We’ll upload more to huggingface if several people prefer that. Info for downloading from wandb can be found in the repo, the easiest way is probably:

# pip install e2e_sae
# Save your wandb api key in .env
from e2e_sae import SAETransformer
model = SAETransformer.from_wandb("sparsify/gpt2/d8vgjnyc")
sae = list(model.saes.values())[0] # Assumes only 1 sae in model, true for all saes in paper
encoder = sae.encoder[0]
dict_elements = sae.dict_elements  # Returns the normalized decoder elements

The wandb ids for different seeds can be found in the geometric analysis script here. That script, along with plot_performance.py, is a good place to see which wandb ids were used for each plot in the paper, as well as the exact code used to produce the plots in the paper (including the cosine sim plots you replicated above).

If you want to avoid the e2e_sae dependency, you can find the raw sae weights in the samples_400000.pt file in the respective wandb run. Just make sure to normalize the decoder weights after downloading (note that this was done before uploading to huggingface so people could load the SAEs into e.g. SAELens without having to worry about it).

If so, I think this is because you might double-count or something?

We do double count in the sense that, if, when comparing the similarity between A and B, element A_i has max cosine sim with B_j, we don't remove B_j from being in the max cosine sim for other elements in A. It's not obvious (to me at least) that we shouldn't do this when summarising dictionary similarity in a single metric, though I agree there is a tonne of useful geometric comparison that isn't covered by our single number. Really glad you're digging deeper into this. I do think there is lots that can be learned here.

 

Btw it's not intuitive to me that the encoder directions might be similar even though the decoder directions are not. Curious if you could share your intuitions here.

Dan BraunΩ450

Thanks Logan!

2. Unlike local SAEs, our e2e SAEs aren't trained on reconstructing the current layer's activations. So at least my expectation was that they would get a worse reconstruction error at the current layer.

Improving training times wasn't our focus for this paper, but I agree it would be interesting and expect there to be big gains to be made by doing things like mixing training between local and e2e+downstream and/or training multiple SAEs at once (depending on how you do this, you may need to be more careful about taking different pathways of computation to the original network).

We didn't iterate on the e2e+downstream setup much. I think it's very likely that you could get similar performance by making tweaks like the ones you suggested.

This is neat, nice work!

I'm finding it quite hard to get a sense at what the actual Loss Recovered numbers you report are, and to compare them concretely to other work. If possible, it'd be very helpful if you shared:

  1. What the zero ablations CE scores are for each model and SAE position. (I assume it's much worse for the MLP and attention outputs than the residual stream?)
  2. What the baseline CE scores are for each model.
Dan BraunΩ473

Nice post.

Pushing back a little on this part of the appendix:

Also, unlike many other capabilities which we might want to evaluate, we don’t need to worry about the possibility that even though the model can’t do this unassisted, it can do it with improved scaffolding--the central deceptive alignment threat model requires the model to think its strategy through in a forward pass, and so if our model can’t be fine-tuned to answer these questions, we’re probably safe.

I'm a bit concerned about people assuming this is true for models going forward. A sufficiently intelligent RL-trained model can learn to distribute its planning across multiple forward passes. I think your claim is true for models trained purely on next-token prediction, and for GPT4-level models which, even though they have an RL component in their training, their outputs are all human-understandable (and incorporated into the oversight process).

But even 12 months from now I’m unsure how confident you could be in this claim for frontier models. Hopefully, labs are dissuaded from producing models which can use uninterpretable scratch pads given how much more dangerous they would be and harder to evaluate.

(These are my own takes, the other authors may disagree)

We briefly address a case that can be viewed as "strategic sycophancy" case in Appendix B in the blog post, which is described similarly to your example.  We indeed classify it as an instance of Deceptive Alignment.
As you mention, this case does have some differences with ideas commonly associated with Deceptive Alignment, notably the difference in behaviour between oversight and non-oversight. But it does share two important commonalities:

  • The model is pursuing a goal that its designers do not want.
  • The model strategically deceives the user (and designer) to further a goal.

Detecting instances of models that share these properties will likely involve using many of the tools and techniques that would be applied to more canonical forms of deceptive alignment (e.g. evals that attempt to alter/hamstring a model and measure behaviour in a plethora of settings, interpretability).

Though, as you mention, preventing/fixing models that exhibit these properties may involve different solutions, and somewhat crude changes to the training signal may be sufficient for preventing strategic sycophancy (though by doing so you might end up with strategic deception towards some other Misaligned goal).

I agree that deception which is not strategic or intentional could be important to prevent. However,

  1. I expect the failure cases in these scenarios to manifest earlier,  making them easier to fix and likely less catastrophic than cases that are strategic and intentional.
  2. Having a definition of Deceptive Alignment that captured every dangerous behaviour related to deception wouldn't be very useful.  We can use "deception” on its own to refer to this set of cases, and reserve terms like Strategic Deception and Deceptive Alignment for subclasses of deception, ideally subclasses that meaningfully narrow the solution space for detection and prevention.

Thanks for sharing that analysis, it is indeed reassuring!

Dan BraunΩ241

Nice project and writeup. I particularly liked the walkthrough of thought processes throughout the project

Decision square's Euclidean distance to the top-right  corner, positive ().

We are confused and don't fully understand which logical interactions produce this positive regression coefficient.

I'd be weary about interpreting the regression coefficients of features that are correlated (see Multicollinearity). Even the sign may be misleading.

It might be worth making a cross-correlation plot of the features. This won't give you a new coefficients to put faith in, but it might help you decide how much to trust the ones you have. It can also be useful looking at how unstable the coefficients are during training (or e.g. when trained on a different dataset).

Hi Nora. We used rapidsai's cuml which has GPU compatibility. Beware, the only "metric" available is "euclidean", despite what the docs say (issue).

I think the risk level becomes clearer when stepping back from stories of how pursuing specific utility functions lead to humanity's demise. An AGI will have many powerful levers on the world at its disposal. Very few combinations of lever pulls result in a good outcome for humans.

From the perspective of ants in an anthill, the actual utility function(s) of the humans is of minor relevance; the ants will be destroyed by a nuclear bomb in much the same way as they will be destroyed by a new construction site or a group of mischievous kids playing around.

(I think your Fermi AGI paradox is a good point, I don't quite know how to factor that into my AGI risk assessment.)

Load More