conftrace_

attention head analysis

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

transformer interpretability (2) semantic induction head (1) knowledge graph relation (1) token embedding tracking (1) safety-utility trade-off (1) semantic induction (1) model behavior analysis (1) large language model (1) attention visualization (1) sparse fine-tuning (1)

Papers

Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis ACL 2026 Identifying Semantic Induction Heads to Understand In-Context Learning ACL 2024 InterpreT: An Interactive Visualization Tool for Interpreting Transformers EACL 2021