What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track
Fixed-SAE Track is introduced, a framework that trains one shared SAE per considered layer on activations pooled across the base model and all RL checkpoints, holding every feature direction fixed so that representation shifts are rigorously defined through the activations of interpretable SAE latents, including the de...
Ling-Heng Du, Yi-Ming Tang, Xufeng Duan et al.
· 1 citation