arXiv (All)
open access
Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens
A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states into tokens. But a lens reading reflects both the hidden state and the readout (the unembedding matrix) used to decode it. Many lenses are fit on a corpu
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
- HumaniBench: A Human-Centric Framework for Large Multimodal Models Evaluation#984856
- AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models#616758
- AlloEgo-VLM: Disambiguating Allocentric and Egocentric Reference Frames in Vision-Language Models#616258
- Distinct roles of central and peripheral vision in rapid scene understanding.#288602
- Chronometric Normalization for BYOD Digital Assessments: Separating Hardware Latency from Cognitive Fluency#1067835
Record · ID 822353
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