conftrace_

attention head

186 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (36) language model (28) attention mechanism (28) mechanistic interpretability (25) vision-language model (14) in-context learning (14) model compression (14) representation learning (14) transformer model (11) transformer architecture (11)

Papers

Circuit Component Reuse Across Tasks in Transformer Language Models ICLR 2024 Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers NeurIPS 2024 Copy Suppression: Comprehensively Understanding a Motif in Language Model Attention Heads EMNLP 2024 Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts in Language Models ACL 2024 Decomposing and Editing Predictions by Modeling Model Computation ICML 2024 Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP NeurIPS 2024 Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers NeurIPS 2024 Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control NeurIPS 2024 Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach ACL 2024 Evidence of Learned Look-Ahead in a Chess-Playing Neural Network NeurIPS 2024 Explorations of Self-Repair in Language Models ICML 2024 Exploring Semantics in Pretrained Language Model Attention NAACL 2024 Fairness-Aware Structured Pruning in Transformers AAAI 2024 Function Vectors in Large Language Models ICLR 2024 How and where does CLIP process negation? ACL 2024 How does GPT-2 Predict Acronyms? Extracting and Understanding a Circuit via Mechanistic Interpretability AISTATS 2024 HydraViT: Stacking Heads for a Scalable ViT NeurIPS 2024 Identifying Semantic Induction Heads to Understand In-Context Learning ACL 2024 In-Context Language Learning: Architectures and Algorithms ICML 2024 Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024 Interpreting and Improving Large Language Models in Arithmetic Calculation ICML 2024 Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis EMNLP 2024 Interpreting CLIP's Image Representation via Text-Based Decomposition ICLR 2024 Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks NeurIPS 2024 LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models ACL 2024