arXiv (All)
open access
When Can We Trust the Sparse Lens? A Certification Framework for SAE Faithfulness
Sparse autoencoders (SAEs) are increasingly used to study internal representations in language models (LMs), but it remains unclear when an SAE-based representation reliably preserves the underlying model's predictive behavior. We introduce a post-hoc certification framework for this purpose. At a c
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
- Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability#1143907
- Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?#1129624
- Representation Risk in Pretrained Image Encoders#1130220
- Test-Time Unlearning via Sparse Autoencoder#1110603
- Language Models Are "Insecure" Reporters#1130981
Record · ID 1117471
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