conftrace_

transformer interpretability

12 papers

Explore in graph

Co-occurring keywords · papers mentioning both

attention head (3) model analysis (3) attention mechanism (3) mechanistic analysis (2) attention head analysis (2) attention visualization (2) attention pattern (2) mechanistic interpretability (2) semantic induction (1) compiled model (1)

Papers

TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors ACL 2026 Discursive Circuits: How Do Language Models Understand Discourse Relations? EMNLP 2025 Quantifying Logical Consistency in Transformers via Query-Key Alignment EMNLP 2025 Human and System Perspectives on the Expression of Irony: An Analysis of Likelihood Labels and Rationales COLING 2024 Identifying Semantic Induction Heads to Understand In-Context Learning ACL 2024 Understanding Addition in Transformers ICLR 2024 Tracr: Compiled Transformers as a Laboratory for Interpretability NeurIPS 2023 Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars NeurIPS 2023 GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers NAACL 2022 InterpreT: An Interactive Visualization Tool for Interpreting Transformers EACL 2021 Self-Attention Attribution: Interpreting Information Interactions Inside Transformer AAAI 2021 Transformer Interpretability Beyond Attention Visualization CVPR 2021