Zeping Yu

awesome-llm-understanding-mechanism. awesome papers in LLM interpretability

srnn. sliced-rnn

awesome-SAE. awesome SAE papers

sli_rec. Python

neuron-attribution. code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models

awesome-LLM-neuron.

in-context-mechanism. code for EMNLP 2024 paper: How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning

arithmetic-mechanism. code for EMNLP 2024 paper: Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis

llava-mechanism. code for arxiv paper: Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering