arXiv (All)
open access
Selecting The Most Informative Tokens in Natural Language Autoencoders
Natural language autoencoders translate a language model's internal activations into readable explanations. Explaining every token position is costly. Which positions should an auditor inspect to understand a potential threat? We study this question across $4.7$ million explanations on prompt inject
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
- Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return Predictions#1143470
- An Empirical Study of Counterfactual Self-Explanations in LLMs#1123509
- Fiction As a Vehicle for Truth: Moving Beyond the Ontic Conception#702256
- What we owe to decision-subjects: beyond transparency and explanation in automated decision-making#80589
- How User-AI Mistreatment Occurs and Matters in Conversational Systems?#1071356
Record · ID 1132241
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