Calibrating Lightweight Sparse Autoencoder Feature Steering
This work introduces ContrastSteer, a complementary heuristic that measures whether post-steering activations emphasize weakly aligned features, thus indicating off-target or nonsensical outputs, and introduces contamination, a complementary heuristic that distinguishes successful steering, under-steering, and over-ste...
Ananya Joshi, C. Cintas, Skyler Speakman
· 1 citation