SAE feature importance

Creator

Creator

Created

Created

2025 Feb 3 13:12

Editor

Editor

Edited

Edited

2025 Feb 3 13:13

Refs

Refs

independent loss contribution a feature makes, and then analyze how much of that specific feature can be recovered?

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-how-much

Recommendations

////////////