Sentences are partially understood before they're fully read. How do LMs incrementally interpret their inputs?

In a new paper, @amuuueller.bsky.social and I use mech interp tools to study how LMs process structurally ambiguous sentences. We show LMs rely on both syntactic & spurious features! 1/10

🚨 PhD position alert! 🚨

I'm hiring a fully funded PhD student to work on mechanistic interpretability at @uva-amsterdam.bsky.social. If you're interested in reverse engineering modern deep learning architectures, please apply: vacatures.uva.nl/UvA/job/PhD-...

Currently writing up a report on the IR summer school that we organized here in Amsterdam. The lectures are publicly available and provide a great introduction to anyone interested in IR. Thought I'd share: 2024.essir.eu/talks