Weakening Neurons: An Input-Output Functionality in Transformers with Outsize Influence

2026-09-16

AI Summary

研究通过计算GLU神经元输入输出权重向量的余弦相似性，发现减弱神经元在大型语言模型的后期层中出现并具有显著影响。

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 (writing) weight vectors. In this scheme, a strong negative cosine similarity indicates the neuron weakens the direction it detects in the residual stream, so we call this a weakening neuron. This allows us to gain a number of novel insights. First, we show that nine different LLMs have similar patterns: weakening neurons appear mostly in late layers whereas their counterparts, (conditional) strengthening neurons, are frequent in early-middle layers. Second, we find that weakening neurons display surprising behavior: even though there are few, they activate often and have a large influence on model behavior. Third, weakening neurons have a strong effect on model output when gate values are negative -- which is surprising since negative gate values are not expected to encode functionality.

Problem

• Weakening Neurons
• Input-Output Functionality
• Transformers
• Large Language Models
• GLU-based neurons

Innovation

• weakening neurons
• cosine similarity
• GLU-based neurons
• large language models
• negative gate values