Will be presenting a new paper on generalizability in mechinterp research at the 2025 NeurIPS MechInterp workshop! Thread below. #NeurIPS

Does vision training change how language is represented and used in meaningful ways?🤔The answer is a nuanced yes! Comparing VLM-LM minimal pairs, we find that while the taxonomic organization of the lexicon is similar, VLMs are better at _deploying_ this knowledge. [1/9]

I think understanding which factors lead to convergence and divergence (both in behavior and internal mechanisms) across networks is crucial to understanding what kinds of systems we're studying and what kinds of claims we can generalize across model instances. Very cool work!

📍Excited to share that our paper was selected as a Spotlight at #NeurIPS2025! arxiv.org/pdf/2410.03972 It started from a question I kept running into: When do RNNs trained on the same task converge/diverge in their solutions? 🧵⬇️

A confounding thing for the linguistics of LMs: the best way to assess their grammatical ability is string probability. Yet string probability and grammaticality are famously not the same! Really excited to have this out, where we give a formal account, w/ experiments, of how to make sense of that!

Hard to process the news about Harvard and international students. Other universities should stand in solidarity with our colleagues who are being persecuted.

Please read my essay in TIME, which @science.org did not do carefully before publishing this assertion. time.com/7285045/resi...

My awesome colleague @seantrott.bsky.social quoted on understanding the nature of our new robot overlords in @nytimes.com www.nytimes.com/2024/12/16/o...