Full Text Available

Note: Clicking the button above will open the full text document at the original institutional repository in a new window.

Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting

Saved in:
Bibliographic Details
Published in:ArXiv cs.LG Recent Papers
Format: Online Article RSS Article
Published: 2026
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864583773381722116
collection WordPress RSS
FRELIP Feed Integration
container_title ArXiv cs.LG Recent Papers
description
discipline_display Engineering & Technology
discipline_facet Engineering & Technology
format Online Article
RSS Article
genre Journal Article
id rss_article:50024
institution FRELIP
journal_source_facet ArXiv cs.LG Recent Papers
publishDate 2026
publishDateSort 2026
record_format rss_article
spellingShingle Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
sub_discipline_display Petroleum & Energy
sub_discipline_facet Petroleum & Energy
subject_display ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
subject_facet ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
title Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
title_auth Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
title_full Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
title_fullStr Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
title_full_unstemmed Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
title_short Superposition Is Not Necessary: A Mechanistic Interpretability Analysis of Transformer Representations for Time Series Forecasting
title_sort superposition is not necessary: a mechanistic interpretability analysis of transformer representations for time series forecasting
topic ArXiv cs.LG Recent Papers
Petroleum & Energy
Engineering & Technology
url https://arxiv.org/abs/2605.05151v1