Interpretability and mechanistic analysis · MLD-1116
SHAP
A family of feature-attribution methods based on Shapley-value ideas and chosen background assumptions.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Explain a prediction with feature contributions.
Original caveat
The background distribution and dependence assumptions affect results.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: SHapley Additive exPlanations.
Related concepts
Concepts linking here
Technology connections
- SHAP — Additive feature-attribution methods and tooling.
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 ↗