Skip to content
Sagan

Paper

Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs

Unreadunread

AI summary

The authors study "feature rivalry"—negatively correlated pairs of SAE (sparse autoencoder) features—as a mechanistic signature of model uncertainty in Gemma-2-2B. They show that high-entropy questions produce significantly stronger rivalry at specific layers than low-entropy questions, and that steering along the rivalry axis (feature A minus feature B) changes outputs more than random directions. A per-prompt rivalry score predicts answer correctness with AUROC 0.689, approaching but not matching softmax confidence at 0.808.

Main takeaways:

  • Feature rivalry is defined as negatively correlated SAE feature pairs; stronger rivalry correlates with higher question entropy (model uncertainty) at layers 0 and 12.
  • Activation steering along the rivalry direction (vector_A − vector_B) causes more output changes than random directions, suggesting rivalry is causally upstream of outputs.
  • A rivalry score computed from pairwise cosine similarities of active SAE features predicts answer correctness (AUROC 0.689 vs. 0.808 for softmax confidence).
  • The results localize uncertainty to specific residual-stream processing stages and suggest SAE features encode uncertainty mechanistically, not just statistically.