news

Sep 03, 2025 I’ll be giving talks on our recent papers on Sparse Autoencoders for Content Control at the Bau Lab at Northeastern (Sept 5), Singh Lab at Brown (Sept 8), and MIT CSAIL (Sept 9). Please join if you’re around!
Aug 20, 2025 Our paper SAEs Are Good for Steering - If You Select the Right Features has been accepted to EMNLP 2025 (Main Conference)!
Aug 04, 2025 I’ll be spending the rest of the summer visiting David Bau’s lab at Northeastern University’s Khoury College of Computer Sciences. If you’re in the area and want to chat about interpretability, feel free to reach out!