arXiv (All)
open access
Understanding Confabulation and Rethinking Reconstruction in Activation Explanations
Natural Language Autoencoders (NLAs) produce unsupervised text explanations of a model's activations: a verbalizer describes an activation and a reconstructor learns to recover it from this text. Under the established point-reconstruction NLA training recipe, explanations become more useful for pred
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
- Levels of explanation reconceived#761471
- Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations#635922
- Train the Model, Not the Reader: Decodability Supervision for Verifiable Activation Explanations#633573
- Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation#798910
- Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation#797496
Record · ID 1118775
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