conftrace_

circuit discovery

14 papers

Explore in graph

Co-occurring keywords

mechanistic interpretability (133) language model (4599) activation patching (23) transformer circuit (3) model interpretability (519) interchange intervention training (2) information flow (49) transformer language model (192) edge pruning (3) discourse relation (121)

Papers

Interpretability Analysis of Arithmetic In-Context Learning in Large Language Models EMNLP 2025
BlackboxNLP-2025 MIB Shared Task: Improving Circuit Faithfulness via Better Edge Selection EMNLP 2025
Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference ACL 2025
Understanding Verbatim Memorization in LLMs Through Circuit Discovery ACL 2025
Discursive Circuits: How Do Language Models Understand Discourse Relations? EMNLP 2025
Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations ICCV 2025
Position-aware Automatic Circuit Discovery ACL 2025
BlackboxNLP-2025 MIB Shared Task: IPE: Isolating Path Effects for Improving Latent Circuit Identification EMNLP 2025
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques NIPS 2024
Finding Transformer Circuits With Edge Pruning NIPS 2024
Optimal ablation for interpretability NIPS 2024
Attribution Patching Outperforms Automated Circuit Discovery EMNLP 2024
Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024
Towards Automated Circuit Discovery for Mechanistic Interpretability NIPS 2023