Interpretability

A diary entry introducing AI interpretability and discussing a paper on the limitations of sparse autoencoders for finding canonical units of analysis in LLMs.

A diary entry on tracing the reasoning processes of Large Language Models (LLMs) to enhance interpretability, and a discussion on the inherent difficulties and challenges in achieving AI alignment.

A diary entry on ‘Thought Anchors’, a concept for identifying key reasoning steps in Chain-of-Thought (CoT) processes that significantly influence LLM behavior, enhancing interpretability for AI safety.

A diary entry on several Anthropic discussions, including AI interpretability, the affective use of AI for emotional support, and the philosophical questions surrounding AI consciousness and model welfare.

A diary entry on Anthropic’s research into Persona Vectors, a method for monitoring and controlling character traits in Large Language Models (LLMs) to improve safety and alignment.