← Search

Nathan W. Henry

2 accepted papers

2026

RepIt: Steering Language Models with Concept-Specific Refusal Vectors

ICLR 2026poster

Current safety evaluations of language models rely on benchmark-based assessments that may miss targeted vulnerabilities. We present RepIt, a simple and data-efficient framework for isolating concept-specific representations in LM activations. While existing steering methods already achieve high att…

Cited by 0SourcecodeScholar
2025

Geometry of Lightning Self-Attention: Identifiability and Dimension

ICLR 2025poster

We consider function spaces defined by self-attention networks without normalization, and theoretically analyze their geometry. Since these networks are polynomial, we rely on tools from algebraic geometry. In particular, we study the identifiability of deep attention by providing a description of t…