跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.18089 · v1

Deep Latents, Long Memory: Latent persistence explains temporal correlations in transformer activations

首次提交 2026-11-13 20:14
版本更新 2026-11-13 20:14
雷达观测 2026-11-16 11:42
arXiv ↗PDF ↗

摘要

The hidden layers of Large Language Models (LLMs) are believed to encode representations of the data whose abstraction increases with depth. However, in the absence of an operational notion of abstraction, this statement is hard to test quantitatively. Here, we propose an alternative view, building on the principle that the correlations of a sequence reflect the structure of the process that generated it. We define the autocorrelation function of a layer as the average dot product between its activations at two context positions separated by a lag. Latent variables encoded persistently along the context create slowly decaying tails in the autocorrelation, and we find these tails to grow across layers in both synthetic and natural data. In synthetic data with controlled hierarchical latent structure, this growth stems from the encoding of abstract latent variables, which govern long stretches of the input. Indeed, the persistence of latent codes predicts the qualitative structure of autocorrelations and accounts for most of the empirical measures. In real text, we take sparse-autoencoder features as proxies for latent variables, and find that their persistence correlates strongly with the magnitude of autocorrelations across datasets and LLMs. In particular, the persistence time increases with depth, as do autocorrelations, implying that deeper latent features persist for longer context spans. We complement this analysis by explicitly ablating the persistent sparse-autoencoder features and observing a consequent decrease in the autocorrelations.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-13 20:14 · 最新观测版本

Deep Latents, Long Memory: Latent persistence explains temporal correlations in transformer activations

The hidden layers of Large Language Models (LLMs) are believed to encode representations of the data whose abstraction increases with depth. However, in the absence of an operational notion of abstraction, this statement is hard to test quantitatively. Here, we propose an alternative view, building on the principle that the correlations of a sequence reflect the structure of the process that generated it. We define the autocorrelation function of a layer as the average dot product between its activations at two context positions separated by a lag. Latent variables encoded persistently along the context create slowly decaying tails in the autocorrelation, and we find these tails to grow across layers in both synthetic and natural data. In synthetic data with controlled hierarchical latent structure, this growth stems from the encoding of abstract latent variables, which govern long stretches of the input. Indeed, the persistence of latent codes predicts the qualitative structure of autocorrelations and accounts for most of the empirical measures. In real text, we take sparse-autoencoder features as proxies for latent variables, and find that their persistence correlates strongly with the magnitude of autocorrelations across datasets and LLMs. In particular, the persistence time increases with depth, as do autocorrelations, implying that deeper latent features persist for longer context spans. We complement this analysis by explicitly ablating the persistent sparse-autoencoder features and observing a consequent decrease in the autocorrelations.

查看此版本解读 →查看此版本原文 ↗