arXiv (All)
open access
Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability
Sparse autoencoders (SAEs) are increasingly scaled to wider dictionaries to recover fine-grained structure from large language model activations. However, a feature is useful for interpretation only if it remains a stable unit of analysis when the same meaning is expressed in different surface forms
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
- When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities#353053
- LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness Nuances#975359
- When Can We Trust the Sparse Lens? A Certification Framework for SAE Faithfulness#1117471
- (Towards) Scalable Reliable Automated Evaluation with Large Language Models#414122
- Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?#1129624
Record · ID 1143907
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