arXiv (All)
open access
How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations
Sparse Autoencoders (SAEs) have found success parsing neural network representations into interpretable concepts, providing a basis for understanding and control. However, what exactly SAEs extract and, hence, the scientific conclusions we can draw from them are not obvious. In short, if your SAE be
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
- The Misery of Mechanistic Interpretability: A Formal Perspective#1109531
- Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures#31283
- Amortizing intractable inference in large language models#798540
- Amortizing intractable inference in large language models#797127
- Stream Recursion Model (SRM)#1076465
Record · ID 1141558
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