This is a series of snippets about the Google DeepMind mechanistic interpretability team's research into Sparse Autoencoders, that didn't meet our bar for a full paper. Please start at the summary post for more context, and a summary of each snippet. They can be read in any order.

Activation Steering with SAEs

Arthur Conmy, Neel Nanda

TL;DR: We use SAEs trained on GPT-2 XL’s residual stream to decompose steering vectors into interpretable features. We find a single SAE feature for anger which is a Pareto-improvement over the anger steering vector from existing work (Section 3, 3 minute read). We have more mixed results with wedding steering vectors: we can partially interpret the vectors, but the SAE reconstruction is a slightly worse steering vector, and just taking the obvious features produces a notably worse vector. We can produce a better steering vector by removing SAE features which are irrelevant (Section 4). This is one of the first examples of SAEs having any success for enabling better control of language models, and we are excited to continue exploring this in future work.

1. Background and Motivation

We are uncertain about how useful mechanistic interpretability research, including SAE research, will be for AI safety and alignment. Unlike RLHF and dangerous capability evaluation (for example), mechanistic interpretability is not currently very useful for downstream applications on models. Though there are ambitious goals for mechanistic interpretability research such as finding safety-relevant features in language models using SAEs, these are likely not tractable on the relatively small base models we study in all our snippets.

To address these two concerns, we decided to study activation steering^[1] (introduced in this blog post and expanded on in a paper). We recommend skimming the blog post for an explanation of the technique and examples of what it can do. Briefly, activation steering takes vector(s) from the residual stream on some prompt(s), and then adds these to the residual stream on a second prompt. This makes outputs from the second forward pass have properties inherited from the first forward pass. There is early evidence that this technique could help with safety-relevant properties of LLMs, such as sycophancy.

We have tentative early research results that suggest SAEs ...

GDM Mech Interp Progress Updates

GDM Mech Interp Progress Updates