Audio note: this article contains 31 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.
Lewis Smith*, Sen Rajamanoharan*, Arthur Conmy, Callum McDougall, Janos Kramar, Tom Lieberum, Rohin Shah, Neel Nanda
The following piece is a list of snippets about research from the GDM mechanistic interpretability team, which we didn’t consider a good fit for turning into a paper, but which we thought the community might benefit from seeing in this less formal form. These are largely things that we found in the process of a project investigating whether sparse autoencoders were useful for downstream tasks, notably out-of-distribution probing.
TL;DR
- To validate whether SAEs were a worthwhile technique, we explored whether they were useful on the downstream task of OOD generalisation when detecting harmful intent in user prompts
- [...]
Outline:
(01:08) TL;DR
(02:38) Introduction
(02:41) Motivation
(06:09) Our Task
(08:35) Conclusions and Strategic Updates
(13:59) Comparing different ways to train Chat SAEs
(18:30) Using SAEs for OOD Probing
(20:21) Technical Setup
(20:24) Datasets
(24:16) Probing
(26:48) Results
(30:36) Related Work and Discussion
(34:01) Is it surprising that SAEs didn't work?
(39:54) Dataset debugging with SAEs
(42:02) Autointerp and high frequency latents
(44:16) Removing High Frequency Latents from JumpReLU SAEs
(45:04) Method
(45:07) Motivation
(47:29) Modifying the sparsity penalty
(48:48) How we evaluated interpretability
(50:36) Results
(51:18) Reconstruction loss at fixed sparsity
(52:10) Frequency histograms
(52:52) Latent interpretability
(54:23) Conclusions
(56:43) Appendix
First published:
March 26th, 2025
Source:
https://www.lesswrong.com/posts/4uXCAJNuPKtKBsi28/sae-progress-update-2-draft)
---
Narrated by TYPE III AUDIO).
Images from the article:
))T3A_INLINE_LATEX_PLACEHOLDER\omega_0=10^{-1}T3A_INLINE_LATEX_END_PLACEHOLDER (middle) or T3A_INLINE_LATEX_PLACEHOLDER\omega_0=10^{-2}T3A_INLINE_LATEX_END_PLACEHOLDER (bottom). The quadratic frequency loss successfully removes high frequency features (i.e. latents around or to the right of the red dotted vertical line) without changing the shape of the rest of the frequency histogram." style="max-width: 100%;" />))T3A_INLINE_LATEX_PLACEHOLDER\omega=0.01___T3A_INLINE_LATEX_END_PLACEHOLDER_. All SAEs show a negative trend of autointerp score against latent frequency, although the quadratic-frequency loss function seems to help the SAE form interpretable latents even at higher frequencies - the curves for higher L0 SAEs are squashed to the right." style="max-width: 100%;" />))))))))
Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts), or another podcast app.
