稀疏自编码器与大型语言模型的整体性
Sparse Auto-Encoders and Holism about Large Language Models
AI总结：
本文探讨LLM是否暗示了语义整体性，通过稀疏自编码器发现的可解释潜在特征挑战了传统整体性观点，最终论证整体性仍具说服力。
摘要：
大型语言模型（LLM）技术是否暗示了语义整体性？本文探讨LLM如何通过分布语义捕捉语言表达的意义，挑战了传统整体性观点。通过稀疏自编码器发现的可解释潜在特征提出了一种分解性语义图景。本文进一步分析这些特征的性质，并论证整体性观点在特征可计数的前提下仍成立。
英文摘要：
Does Large Language Model (LLM) technology suggest a meta-semantic picture i.e. a picture of how words and complex expressions come to have the meaning that they do? One modest approach explores the assumptions that seem to be built into how LLMs capture the meanings of linguistic expressions as a way of considering their plausibility (Grindrod, 2026a, 2026b). It has previously been argued that LLMs, in employing a form of distributional semantics, adopt a form of holism about meaning (Grindrod, 2023; Grindrod et al., forthcoming). However, recent work in mechanistic interpretability presents a challenge to these arguments. Specifically, the discovery of a vast array of interpretable latent features within the high dimensional spaces used by LLMs potentially challenges the holistic interpretation. In this paper, I will present the original reasons for thinking that LLMs embody a form of holism (section 1), before introducing recent work on features generated through sparse auto-encoders, and explaining how the discovery of such features suggests an alternative decompositional picture of meaning (section 2). I will then respond to this challenge by considering in greater detail the nature of such features (section 3). Finally, I will return to the holistic picture defended by Grindrod et al. and argue that the picture still stands provided that the features are countable (section 4).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
