conftrace_

transformer circuit

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

mechanistic interpretability (3) circuit discovery (2) language model (2) verbatim memorization (1) numerical comparison (1) cross-model comparison (1) sparse subgraph (1) circuit universality (1) large language model (1) edge pruning (1)

Papers

Mechanistic Analysis Of Universality: Numerical Comparison Circuits Across Transformer Architectures ACL 2026 Understanding Verbatim Memorization in LLMs Through Circuit Discovery ACL 2025 Finding Transformer Circuits With Edge Pruning NeurIPS 2024