Interpretability and mechanistic analysis · MLD-0878
Partial dependence plot
A plot averaging model predictions as selected features vary over the data distribution.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Visualize a feature's average modeled effect.
Original caveat
Correlated features can produce unrealistic input combinations.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: PDP.
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 ↗