conftrace_

mechanistic interpretability

133 papers

Explore in graph

Also known as

MI

Co-occurring keywords

large language model (13587) language model (4599) sparse autoencoder (112) attention head (146) neural network (6616) circuit analysis (17) in-context learning (1405) circuit discovery (14) attention mechanism (4001) activation patching (23)

Papers

A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations ICML 2023
Analyzing Vision Transformers for Image Classification in Class Embedding Space NIPS 2023
Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models EMNLP 2023
Tracr: Compiled Transformers as a Laboratory for Interpretability NIPS 2023
Towards Automated Circuit Discovery for Mechanistic Interpretability NIPS 2023
How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model NIPS 2023
Learning Transformer Programs NIPS 2023
Tracing and Manipulating intermediate values in Neural Math Problem Solvers EMNLP 2022