arXiv (All)
open access
Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers
Massive activation features (MAs) in Transformers are extreme-value residual-stream features that persist across layers despite the model's ability to suppress them. Why do they survive? Our investigation using an operator-level mechanistic analysis of attention and feed-forward (FFN) blocks reveals
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
- Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers#1108762
- Locating Answer-Correctness Signals in Frozen Large Language Models#1142012
- The Life Cycle of a Massive Activation: Stochastic Birth, Weight-Decay-Driven Growth, and Competitive Consolidation#1155358
- Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models#1117139
- Transformer MLP Gate Thresholds Are Couplings to a Carried Reference Direction#1115912
Record · ID 1130284
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