In neuroscience, we often try to understand systems by analyzing their representations — using tools like regression or RSA. But are these analyses biased towards discovering a subset of what a system represents? If you're interested in this question, check out our new commentary! Thread:

If you're at #ICML2025, chat with me, @sarah-nlp.bsky.social, Atticus, and others at our poster 11am - 1:30pm at East #1205! We're establishing a 𝗠echanistic 𝗜nterpretability 𝗕enchmark. We're planning to keep this a living benchmark; come by and share your ideas/hot takes!

The new "Lookback" paper from @nikhil07prakash.bsky.social‬ contains a surprising insight... 70b/405b LLMs use double pointers, akin to C programmers' double (**) pointers. They show up when the LLM is "knowing what Sally knows Ann knows", i.e., Theory of Mind. bsky.app/profile/nik...

SAEs have been found to massively underperform supervised methods for steering neural networks. In new work led by @danaarad.bsky.social, we find that this problem largely disappears if you select the right features!

Tried steering with SAEs and found that not all features behave as expected? Check out our new preprint - "SAEs Are Good for Steering - If You Select the Right Features" 🧵

Couldn’t be happier to have co-authored this will a stellar team, including: Michael Hu, @amuuueller.bsky.social, @alexwarstadt.bsky.social, @lchoshen.bsky.social, Chengxu Zhuang, @adinawilliams.bsky.social, Ryan Cotterell, @tallinzen.bsky.social

Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work? We propose 😎 𝗠𝗜𝗕: a 𝗠echanistic 𝗜nterpretability 𝗕enchmark!

Lots of work coming soon to @iclr-conf.bsky.social and @naaclmeeting.bsky.social in April/May! Come chat with us about new methods for interpreting and editing LLMs, multilingual concept representations, sentence processing mechanisms, and arithmetic reasoning. 🧵

It’s common to assume one task = one static circuit. But this ignores that the important computations depend on position! We propose a way to find 𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻-𝗮𝘄𝗮𝗿𝗲 circuits. (Highlight: using LLMs to help us create multi-token causal abstractions!)

What can mechanistic interpretability do for computational psycholinguists? @michaelwhanna.bsky.social and I took a stab at this question! We investigate garden path sentence processing in LMs at the feature (circuit) level.

Today we had the pleasure to host @michaelwhanna.bsky.social from @amsterdamnlp.bsky.social for a seminar on his work w/ @amuuueller.bsky.social to interpret incremental sentence processing in language models. Thank you for joining us Michael!

The babies are now in their beds, but what a year it was! Highlighting some findings of BabyLM Architectures & Training objective matter a lot (and got the highest scores) alphaxiv.org/pdf/2410.24159 🤖

How do language models organize concepts and their properties? Do they use taxonomies to infer new properties, or infer based on concept similarities? Apparently, both! 🌟 New paper with my fantastic collaborators @amuuueller.bsky.social and @kanishka.bsky.social