arXiv (All)
open access
Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition
Linear probes can decode safety-relevant concepts such as truthfulness from language-model activations, but probe accuracy may show only decodability, not that the features the probe weights causally drive model behavior. We demonstrate that this gap cannot be closed from the geometry of probe weigh
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
- ReBeCA: Unveiling Interpretable Behavior Hierarchy behind the Iterative Self-Reflection of Language Models with Causal Analysis#974322
- Refusal Localizes, the Damage Relocates: Safety Layers Under Few-Sample Fine-Tuning#1154943
- Beyond Decodability: Reconstructing Language Model Representations with an Encoding Probe#926019
- Many Worlds as Anti-Conspiracy Theory: Locally and causally explaining a quantum world without finetuning#118501
- Causality and Dependence as Container Projections#90479
Record · ID 1011781
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