sae-features

Tag

Cards List
#sae-features

Measuring Semantic Abstractness of SAE Features via Nonlocality

arXiv cs.AI · 5d ago Cached

This paper introduces Feature Nonlocality (FNL), an entropy-based metric for measuring the semantic abstractness of SAE features in LLMs, and demonstrates applications in auditing jailbreak mitigation features and improving MATH-500 accuracy via steering.

0 favorites 0 likes
← Back to home

Submit Feedback