arXiv (All)
open access
The Geometry of Inference in Transformer Residual Streams
Transformer language models build predictions through successive residual updates, but how their representations become specific to an eventual outcome remains unclear. We study this process by comparing intermediate residual states with their own final states and an empirical bank of final states f
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
- Amortizing intractable inference in large language models#798540
- Amortizing intractable inference in large language models#797127
- Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference#1116817
- A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability#793258
- A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability#789254
Record · ID 1142132
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