Interpretability and mechanistic analysis · MLD-1117
Shapley value
A cooperative-game allocation rule averaging a participant's marginal contribution across coalitions.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Allocate predictive contribution among features.
Original caveat
Computational approximations and feature-dependence choices matter.
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 ↗