circuit analysis

Circuit-Think: A Multimodal Reasoning Framework for Automated Circuit-to-Netlist Translation with Trajectory-Guided Reinforcement Learning AAAI 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 Uncovering Sentiment Analysis Circuit in Large Language Model ACL 2026 Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics ICLR 2025 Circuit-Tracer: A New Library for Finding Feature Circuits EMNLP 2025 Does Time Have Its Place? Temporal Heads: Where Language Models Recall Time-specific Information ACL 2025 Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning NAACL 2025 Neuroplasticity and Corruption in Model Mechanisms: A Case Study Of Indirect Object Identification NAACL 2025 The Same but Different: Structural Similarities and Differences in Multilingual Language Modeling ICLR 2025 The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate It EMNLP 2025 Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis ICML 2025 Circuit Component Reuse Across Tasks in Transformer Language Models ICLR 2024 How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability AISTATS 2024 Hypothesis Testing the Circuit Hypothesis in LLMs NeurIPS 2024 Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024 LLM Circuit Analyses Are Consistent Across Training and Scale NeurIPS 2024 On the Similarity of Circuits across Languages: a Case Study on the Subject-verb Agreement Task EMNLP 2024 Optimization Algorithm Design via Electric Circuits NeurIPS 2024 Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models EMNLP 2024 Transcoders find interpretable LLM feature circuits NeurIPS 2024