arXiv (All)
open access
Evaluating the Causal Faithfulness of SHAP as a Candidate Attribution Method for SAE Features
Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predominantly correlational. Attribution methods offer more direct estimates of feature influence, yet their faithfulness to actual causal effects has not b
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Structure-agnostic Causal Representation Learning#1155903
- Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths#1357781
- Causal Integrated Gradients: Scalable Feature Attribution Along Causal Paths#1348865
- Unifying causal representation learning with the invariance principle#1358927
- How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations#1141558
Record · ID 1343097
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive