arXiv (All)
open access
Beyond Token Scale: Chunk-Level Sparse Autoencoders for Reliable Semantic Feature Discovery
Sparse autoencoders (SAEs) expose features that help us understand and steer language models, but faithful reconstruction does not guarantee informative concepts. Token-level objectives reward lexical and formatting details alongside semantic content, all competing for a limited sparse budget. We in
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 Holistic Storage of Verb+Up Phrases in Text-based and Audio-based Language Models#1116331
- Generalising from Self-Produced Data: Model Training Beyond Human Constraints#1143592
- Leveraging Synthetic Data from Large Language Models to Steer and Enhance Model Learning#929396
- SpecCoder: Specification-Aware Code Generation with Curriculum Dual-Task Reinforcement Learning#973651
- Graph Your Own Prompt#1129118
Record · ID 1130102
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