🔥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

📢📢 Just two days left until our Summit on Open Problems for AI in Boston: algopreneurship.ai Algorithms (4th Dec), Ethics & Society (5th), and Applications & Entrepreneurship (6th) at the awesome Museum of Science. We've got a great set of topics, stellar line-up, and

I'll be at NeurIPS Conference from Monday until Friday next week to present this work. If you'd like to chat about mechinterp, cognitive science, or anything else, feel free to DM me!

Watch this special debate live tomorrow at 10:30 a.m. PT — part of our workshop on Unknown Futures of Generalization. Register to attend in person, access the livestream, or view the recording before it's captioned for publication: simons.berkeley.edu/web-registrati…

Can we find circuits directly from a model’s params? At Neurips I’m presenting work on understanding how attn heads in LMs communicate by analyzing their weights. We find a lot of interesting things, like a 3D subspace that controls which index in a list to attend to!

📢Abstract submissions extended to 16th March AOE for our Annual Conference on the Mathematics of Neuroscience and AI (May 27-30th; National Opera Theatre, Split, Croatia) We have a truly outstanding line-up of keynotes, session chairs, and invited speakers, and would love to

📢A few days left to submit an abstract for our conference on the Mathematics of Neuroscience and AI in sunny Split (May 27-30th)! Thanks to everyone that has submitted so far---the quality has been exceptional! Link in comments below:

Train your vision SAE on Monday, then again on Tuesday, and you'll find only about 30% of the learned concepts match. ⚓ We propose Archetypal SAE which anchors concepts in the real data’s convex hull, delivering stable and consistent dictionaries. arxiv.org/pdf/2502.12892…

AI models appear to mimic the real world. But how can we tell if they truly understand it? Excited to announce the ICML 2025 Workshop on Assessing World Models! Working on related questions? Submit a paper (max. 4 pages) by May 20!

I will be at #ICLR2025 in a few days to present this work with Suraj Anand! Feel free to DM me if you want to chat about mechinterp, cognitive science, or anything else!

Excited to be at #ICLR2025 in a few days to present this work with Michael Lepori! Interested in chatting about training dynamics, mechinterp, memory-efficient training, info theory or anything else! Please dm me.

Announcing the ICML 2025 workshop on Assessing World Models: Methods and Metrics for Evaluating Understanding 🌍 Submit your 4-page papers by May 20, 2025!

Excited to announce I'll be starting as an assistant professor at TTIC for fall 2026! In the meantime, I'll be graduating and hanging around Ai2 in Seattle🏔️

I had a great time helping out on this project with Jennifer Hu and Michael Franke! If you're interested in the intersection of interpretability and cogsci, check it out!

What are the organizing dimensions of language processing? We show that voxel responses are organized along 2 main axes: processing difficulty & meaning abstractness—revealing an interpretable, topographic representational basis for language processing shared across individuals.

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

How do VLMs balance visual information presented in-context with linguistic priors encoded in-weights? In this project, Michal Golovanevsky and William Rudman find out! My favorite result: you can find a vector that shifts attention to image tokens and changes the VLM's response!

Join us for the Workshop on Assessing World Models at ICML tomorrow! When: Friday July 17, 8:45am-5:15pm Where: West Ballroom B (same floor as registration)