PulseAugur
实时 10:14:02
English(EN) Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence

新研究发现大型语言模型中具有巨大影响的“削弱神经元”

研究人员在大型语言模型中发现了一种特殊的神经元,称为“削弱神经元”,它们在模型的输出中起着重要作用。这些神经元主要存在于 Transformer 模型后期层中,其输入和输出权重向量之间表现出负余弦相似度。尽管这些削弱神经元相对稀少,但它们激活频繁,并对模型的行为产生重大影响,尤其是在门控值为负时。 AI

影响 这项研究为分析大型语言模型的内部机制提供了一种新方法,有望提高模型的解释性和可控性。

排序理由 该集群包含一篇详细介绍 Transformer 模型内部工作原理研究发现的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新研究发现大型语言模型中具有巨大影响的“削弱神经元”

本文如何被排名

Signal score
11 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍 Transformer 模型内部工作原理研究发现的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, model release
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Sebastian Gerstner, Hilal AlQuabeh, Kentaro Inui, Hinrich Sch\"utze ·

    弱化神经元:Transformer 中具有巨大影响的输入-输出功能

    arXiv:2609.18612v1 Announce Type: cross Abstract: We analyze the learned input-output behavior of GLU-based neurons in large language models (LLMs). We propose a simple analysis method: For each neuron, we compute the cosine similarities between its input (reading) and output (wr…