Explainability
Mediation Analysis
Traces causal pathways through model (e.g., Causal Mediation Analysis)
1 technique in this subcategory
1 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Causal Mediation Analysis in Language Models | Mechanistic Interpretability | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +3 | Text | Causal mediation analysis in language models is a mechanistic interpretability technique that systematically... |
Rows per page
Page 1 of 1