arXiv (All)
open access
Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction
The corpus-mean direction of a transformer's residual stream is a component shared across all inputs, and is commonly removed by mean-centering before representational analysis. We present evidence that it is a functional component: the reference against which the MLP gate population sets its operat
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
- A Unified Perspective on the Dynamics of Deep Transformers#1120649
- When Attention Fails: Structured Latent Projection Bridging Transformer Degeneration for Time Series Forecasting#381265
- DPRM: A Plug-in Doob h transform-induced Token-Ordering Module for Diffusion Language Models#138951
- Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It#1131786
- The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation#1155358
Record · ID 1115912
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