conftrace_

llm interpretability

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) polysemous word (1) causal gradient variation (1) mechanism interpretability (1) monosemantic feature (1) task-specific neuron (1) neuron localization (1) grounded explanation (1) reasoning behavior (1) causal analysis (1)

Papers

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words ICLR 2025 Does Large Language Model Contain Task-Specific Neurons? EMNLP 2024 XplainLLM: A Knowledge-Augmented Dataset for Reliable Grounded Explanations in LLMs EMNLP 2024