Interpretability and mechanistic analysis · MLD-0423
Feature splitting
A learned feature dividing into more specific features as representation or dictionary capacity increases.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Compare sparse autoencoders of different widths.
Original caveat
Splitting patterns are empirical, not guaranteed semantic hierarchies.
Context and aliases
Level: Advanced. Stages: Research · Evaluation.
Tags: ML · DL · SLM · LLM · Interpretability · Safety.
Aliases: None recorded.
Related concepts
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 ↗