Automated Interpretability

Creator

Creator

Created

Created

2024 Apr 7 15:23

Editor

Editor

Edited

Edited

2025 Feb 19 13:22

Refs

Refs

Automated Steering

Automated Interpretability Techniques

LLM Neuron explainer

Closest Token Lists

Circuit Discovery

Automated interpretability is a difficult task for models that we have only begun working on, it has already been very useful for quickly understanding dictionary learning features in a scalable fashion.

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Mechanistic interpretability seeks to understand neural networks by breaking them into components that are more easily understood than the whole. By understanding the function of each component, and how they interact, we hope to be able to reason about the behavior of the entire network. The first step in that program is to identify the correct components to analyze.

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

https://transformer-circuits.pub/2023/monosemantic-features#appendix-automated

Rubric for human annotator (evaluating interpretability description)

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Mechanistic interpretability seeks to understand neural networks by breaking them into components that are more easily understood than the whole. By understanding the function of each component, and how they interact, we hope to be able to reason about the behavior of the entire network. The first step in that program is to identify the correct components to analyze.

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

https://transformer-circuits.pub/2023/monosemantic-features#appendix-rubric

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

Mechanistic interpretability seeks to understand neural networks by breaking them into components that are more easily understood than the whole. By understanding the function of each component, and how they interact, we hope to be able to reason about the behavior of the entire network. The first step in that program is to identify the correct components to analyze.

Towards Monosemanticity: Decomposing Language Models With Dictionary Learning

https://transformer-circuits.pub/2023/monosemantic-features#global-analysis-interp

Recommendations

/////////