Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers
Paper recorded by Signals 4 on 2026-09-28 in cs.CL. Abstract reproduced from arXiv; link to the original below.
Published 2026-09-28 on arXiv · recorded by Signals 4 on 2026-09-29
Category: cs.CL · 自然语言处理 · first seen 2026-09-29
Abstract
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 that these blocks systematically ignore MA coordinates while reading, but not while writing; creati
Read on arXiv →
Cite this page: Which the Eye Fears: Writing with Read-Blindness Explains Massive Activations in Transformers: the #9 most recent of 279 cs.CL papers we have recorded (as of 2026-09-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/which-the-eye-fears-writing-with-read-blindness-explains-massive-activations-in-.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable:
papers.json
Get 4 AI signals a day by email — free.
Get 4 AI signals a day by email — free