2 papers
cs.LG2025
Interpreting Large Text-to-Image Diffusion Models with Dictionary Learning
Stepan Shabalin, Ayush Panda, Dmitrii Kharlapenko +3
Sparse autoencoders are a promising new approach for decomposing language model activations for interpretation and control. They have been applied successfully to vision transforme…
cs.AI2025
Patterns and Mechanisms of Contrastive Activation Engineering
Yixiong Hao, Ayush Panda, Stepan Shabalin +1
Controlling the behavior of Large Language Models (LLMs) remains a significant challenge due to their inherent complexity and opacity. While techniques like fine-tuning can modify…