arXiv (All)
open access
The Signs Were Always There: Training-Free Detection and Control in Raw Transformer Dimensions
Because of polysemanticity and superposition, it has been challenging to attribute token understanding and generation to specific neurons or dimensions. Yet the information in the hidden states is so rich that the signs of the residual stream can surface semantic content in early layers and control
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
- Growing to See: Efficient Pretraining of Self-Supervised Vision Transformers#1341700
- Understanding In-context Learning of Addition via Activation Subspaces#1034653
- The Geometry of Inference in Transformer Residual Streams#1142132
- Coarse-Graining Hidden Representations: Unsupervised Neuron Selection via Mapping Entropy#660821
- Scalable Circuit Learning for Interpreting Large Language Models#1296443
Record · ID 1400958
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