arXiv (All)
open access
A Testable Theory of Atomic Features
We develop and test a theory of language model representations in which there exist atomic features. Our main theoretical insight is that in such a model, sparse dictionaries (e.g., SAEs) of increasing size recover an increasing prefix of the most prevalent atoms in the training data. This "recovery
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
- On the Recoverability of Private Information Unlearning in Large Language Models#799191
- On the Recoverability of Private Information Unlearning in Large Language Models#797768
- Do Large Language Models Capture the Diversity in their Training Data?#924174
- Do Large Language Models Capture the Diversity in their Training Data?#919943
- Detectable Only Where It Is Confounded: What Verified Duplication Counts Say About Membership Evidence in Language Models#997811
Record · ID 1202213
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