conftrace_

circuit analysis

17 papers

Explore in graph

Co-occurring keywords

mechanistic interpretability (133) large language model (13587) attention head (146) language model (4599) sparse autoencoder (112) neural network (6616) mechanistic analysis (20) feature circuit (2) model interpretability (519) model behavior (26)

Papers

Circuit-Think: A Multimodal Reasoning Framework for Automated Circuit-to-Netlist Translation with Trajectory-Guided Reinforcement Learning AAAI 2026
Uncovering Sentiment Analysis Circuit in Large Language Model ACL 2026
Emergence of Minimal Circuits for Indirect Object Identification in Attention-Only Transformers ACL 2026
KCLNet: Electrically Equivalence-Oriented Graph Representation Learning for Analog Circuits AAAI 2026
Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning NAACL 2025
The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It EMNLP 2025
Circuit-Tracer: A New Library for Finding Feature Circuits EMNLP 2025
Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification NAACL 2025
Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information ACL 2025
Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024
Optimization Algorithm Design via Electric Circuits NIPS 2024
Hypothesis Testing the Circuit Hypothesis in LLMs NIPS 2024
How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability AISTATS 2024
Transcoders find interpretable LLM feature circuits NIPS 2024
On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task EMNLP 2024
LLM Circuit Analyses Are Consistent Across Training and Scale NIPS 2024
Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models EMNLP 2024