arXiv (All)
open access
What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions
Sparse autoencoder (SAE) features are typically discovered from how their activations co-vary with behaviour, yet they are often used through interventions such as steering or ablation. We take intervention attribution, the first-order effect of a specified intervention on the model output, as our e
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
- From Input to Output: A Flexible Agent for Dual-End Interpretation of Sparse Autoencoder Features#1129959
- SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization#999806
- ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity#1199294
- Do Sparse Autoencoders Learn Meaningful Concept Hierarchies?#1217501
- Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility#1355073
Record · ID 1327100
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