CRL Paper

Steering on correlated sae features improve benchmmakrs not only probing

CRL (Control model training with RL), CTRL (Control model Training with RL)

• SPOT (Sparse Policy Optimization for Circuit control)

• OSCAR (Optimizing Sparse Circuits via Autoencoder Reinforcement)

Connected papers

Connected Papers | Find and explore academic papers

A unique, visual tool to help researchers and applied scientists find and explore papers relevant to their field of work.

https://www.connectedpapers.com/