Interpretability and mechanistic analysis · MLD-0309
Dictionary learning
Learning basis-like elements so data can be represented as sparse combinations of them.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Learn feature directions from neural activations.
Original caveat
The learned dictionary is not a word-definition dictionary.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: None recorded.
Related concepts
Concepts linking here
Original references
- Captum model interpretability documentation ↗ · Reference link
- Tracing the thoughts of a large language model ↗ · Consulted
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learning ↗ · Consulted
- SHAP documentation ↗ · Reference link
- Original reference URL ↗