Interpretability and mechanistic analysis · MLD-0569
Integrated gradients
An attribution method integrating input gradients along a path from a baseline to the input.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Attribute an image classifier's score to pixels.
Original caveat
Baseline and path choices influence interpretation.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: IG.
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 ↗