arXiv (All)
open access
Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models
Mechanistic interpretability often relies on the Linear Representation Hypothesis (LRH), which assumes that high-level concepts are encoded as linear directions in activation space. Yet a natural visual concept does not necessarily require a linear visual transition: between sunny and stormy lies an
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
- RAVE: Re-Allocating Visual Attention in Large Multimodal Models#1035496
- Imag-Eval: a language-grounded framework for interpretable Text-to-Image instruction following evaluation#794023
- Imag-Eval: a language-grounded framework for interpretable Text-to-Image instruction following evaluation#790004
- World Models Meet Language Models: On the Complementarity of Concrete and Abstract Reasoning#798936
- Interpreting Language Model Parameters#1355737
Record · ID 1216027
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