Mechanistic Interpretability

7 posts · 2 sources

BasetenBlog15 Aug

Fine-tuning small open-source LLMs to outperform large closed-source models by 60% on specialized tasks

AnthropicBlog21 May

Mapping the mind of a large language model

AnthropicBlog5 Oct

Decomposing Language Models Into Understandable Components

AnthropicBlog19 Dec

Tracing Model Outputs to the Training Data

AnthropicBlog21 May

Scaling Laws and Interpretability of Learning from Repeated Data

AnthropicBlog8 Mar

In-context Learning and Induction Heads

AnthropicBlog22 Dec

A Mathematical Framework for Transformer Circuits