Chris Wendler

Discovering Forbidden Topics in Language Models

Localized Cultural Knowledge is Conserved and Controllable in Large Language Models

The Geometry of Self-Verification in a Task-Specific Reasoning Model

Steering Diffusion Transformers with Sparse Autoencoders

In-Context Learning Without Copying

zip2zip: Inference-Time Adaptive Tokenization via Online Compression

One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models

Controllable Context Sensitivity and the Knob Behind It

Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders