🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

I'm recruiting PhD students for our new lab, coming to Boston University in Fall 2025! Our lab aims to understand, improve, and precisely control how language is learned and used in natural language systems (such as language models). Details below!

Check out the First Workshop on Mech Interp for Vision at #CVPR2025! Paper submissions: sites.google.com/view/miv-cvpr2…

Ok, so I can finally talk about this! We spent the last year (actually a bit longer) training an LLM with recurrent depth at scale. The model has an internal latent space in which it can adaptively spend more compute to think longer. I think the tech report ...🐦‍⬛

Meet Ai2 Paper Finder, an LLM-powered literature search system. Searching for relevant work is a multi-step process that requires iteration. Paper Finder mimics this workflow — and helps researchers find more papers than ever 🔍

🎉 Our Actionable Interpretability workshop has been accepted to #ICML2025! 🎉 >> Follow Actionable Interpretability Workshop ICML2025 Tal Haklay Anja Reusch Marius Mosbach Sarah Wiegreffe Ian Tenney (@[email protected]) Mor Geva Paper submission deadline: May 9th!

Interested in mechanistic interpretability? We'll be presenting our work on arithmetic mechanisms in LLMs later this week at #ICLR2025. DM me if you're there and want to chat about AI interpretability. 📆Friday, April 25th, 10-12:30 (Poster #243) 🔖iclr.cc/virtual/2025/p…

Having a standard benchmark is important as mechinterp matures. Check out our work and come chat with us at @iclr2025!

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" 🧵

Mateusz and I are excited to announce circuit-tracer, a library that makes circuit-finding simple! Just type in a sentence, and get out a circuit showing (some of) the features your model uses to predict the next token. Try it on neuronpedia: shorturl.at/SUX2A

Now accepted to #COLM2025! We formally define hidden knowledge in LLMs and show its existence in a controlled study. We even show that a model can know the answer yet fail to generate it in 1,000 attempts 😵 Looking forward to presenting and discussing our work in person.