arXiv (All)
open access
Attention Sinks Induce Gradient Sinks: Massive Activations as Gradient Regulators in Transformers
Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focused on the forward pass, yet in pre-norm Transformers, large residual-stream norms play only an indirect forward role because sublayers operate on normali
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
- The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation#1155358
- Force without transmission: a depth-induced rank collapse that no loss on the representation reopens#1234325
- Counting with Attention and LayerNorm: Norm Scaling and Representation Geometry#1341542
- Training Dynamics of Transformers on Unbounded Inputs: Attention Learning Can Lag Output Layer Learning#1355265
Record · ID 1400865
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