In LLMs, concepts aren’t static: they evolve through time and have rich temporal dependencies. We introduce Temporal Feature Analysis (TFA) to separate what's inferred from context vs. novel information. A big effort led by @ekdeepl.bsky.social, @sumedh-hindupur.bsky.social, @canrager.bsky.social!

✨ The schedule for our INTERPLAY workshop at COLM is live! ✨ 🗓️ October 10th, Room 518C 🔹 Invited talks from @sarah-nlp.bsky.social John Hewitt @amuuueller.bsky.social @kmahowald.bsky.social 🔹 Paper presentations and posters 🔹 Closing roundtable discussion. Join us in Montréal! @colmweb.org

What's the right unit of analysis for understanding LLM internals? We explore in our mech interp survey (a major update from our 2024 ms). We’ve added more recent work and more immediately actionable directions for future work. Now published in Computational Linguistics!

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