Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Yıldırım, Alper
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

The Geometric Inductive Bias of Grokking: Bypassing Phase Transitions via Architectural Topology
by: Yıldırım, Alper
Published: (2026)

Language as a Wave Phenomenon: Semantic Phase Locking and Interference in Neural Networks
by: Yıldırım, Alper, et al.
Published: (2025)

DRFormer: Multi-Scale Transformer Utilizing Diverse Receptive Fields for Long Time-Series Forecasting
by: Ding, Ruixin, et al.
Published: (2024)

Evaluating the effectiveness of predicting covariates in LSTM Networks for Time Series Forecasting
by: Davies, Gareth
Published: (2024)

Inter-Series Transformer: Attending to Products in Time Series Forecasting
by: Cristian, Rares, et al.
Published: (2024)

Robust Multivariate Time Series Forecasting against Intra- and Inter-Series Transitional Shift
by: He, Hui, et al.
Published: (2024)

FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
by: Tian, Tian, et al.
Published: (2025)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
by: Hedar, Abdel-Rahman, et al.
Published: (2024)

TS-ACL: Closed-Form Solution for Time Series-oriented Continual Learning
by: Li, Jiaxu, et al.
Published: (2024)

Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction
by: Ribeiro, José, et al.
Published: (2022)

Noise or Signal? Deconstructing Contradictions and An Adaptive Remedy for Reversible Normalization in Time Series Forecasting
by: Fu, Fanzhe, et al.
Published: (2025)

DecompKAN: Decomposed Patch-KAN for Long-Term Time Series Forecasting
by: Mysore, Naveen
Published: (2026)

Load and Renewable Energy Forecasting Using Deep Learning for Grid Stability
by: Sarkar, Kamal
Published: (2025)

Entropy Causal Graphs for Multivariate Time Series Anomaly Detection
by: Febrinanto, Falih Gozi, et al.
Published: (2023)

A Set-Sequence Model for Time Series
by: Epstein, Elliot L., et al.
Published: (2025)

GCAD: Anomaly Detection in Multivariate Time Series from the Perspective of Granger Causality
by: Liu, Zehao, et al.
Published: (2025)

A Learnable Multi-views Contrastive Framework with Reconstruction Discrepancy for Medical Time-Series
by: Wang, Yifan, et al.
Published: (2025)

The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary
by: Guo, Dongxin, et al.
Published: (2026)

Interpretability-Guided Bi-objective Optimization: Aligning Accuracy and Explainability
by: Fouladi, Kasra, et al.
Published: (2026)

A Hybrid Model for Stock Market Forecasting: Integrating News Sentiment and Time Series Data with Graph Neural Networks
by: Sadek, Nader, et al.
Published: (2025)

Prototype Transformer: Towards Language Model Architectures Interpretable by Design
by: Yordanov, Yordan, et al.
Published: (2026)

Causal Discovery in Semi-Stationary Time Series
by: Gao, Shanyun, et al.
Published: (2024)

Generative and Contrastive Graph Representation Learning
by: Chen, Jiali, et al.
Published: (2025)

Decentralized Time Series Classification with ROCKET Features
by: Casella, Bruno, et al.
Published: (2025)

Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
by: Lin, Zezheng, et al.
Published: (2026)

One Router to Route Them All: Homogeneous Expert Routing for Heterogeneous Graph Transformers
by: Shakirov, Georgiy, et al.
Published: (2025)

Weakly Supervised Distillation of Hallucination Signals into Transformer Representations
by: Salehmohamed, Shoaib Sadiq, et al.
Published: (2026)

LaT-PFN: A Joint Embedding Predictive Architecture for In-context Time-series Forecasting
by: Verdenius, Stijn, et al.
Published: (2024)

Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
by: Xu, Yongzhong
Published: (2026)

Causal Discovery-Driven Change Point Detection in Time Series
by: Gao, Shanyun, et al.
Published: (2024)

TimeCatcher: A Variational Framework for Volatility-Aware Forecasting of Non-Stationary Time Series
by: Chen, Zhiyu, et al.
Published: (2026)

Time-to-Injury Forecasting in Elite Female Football: A DeepHit Survival Approach
by: Catterall, Victoria, et al.
Published: (2026)

Shattered Compositionality: Counterintuitive Learning Dynamics of Transformers for Arithmetic
by: Zhao, Xingyu, et al.
Published: (2026)

On the Role of Pre-trained Embeddings in Binary Code Analysis
by: Maier, Alwin, et al.
Published: (2025)

A Self-explainable Model of Long Time Series by Extracting Informative Structured Causal Patterns
by: Wang, Ziqian, et al.
Published: (2025)

RHiOTS: A Framework for Evaluating Hierarchical Time Series Forecasting Algorithms
by: Roque, Luis, et al.
Published: (2024)

Task-Conditioned Routing Signatures in Sparse Mixture-of-Experts Transformers
by: Avinash, Mynampati Sri Ranganadha
Published: (2026)

NoRIN: Backbone-Adaptive Reversible Normalization for Time-Series Forecasting
by: Zhang, Shun, et al.
Published: (2026)

What Do World Models Learn in RL? Probing Latent Representations in Learned Environment Simulators
by: Zhang, Xinyu
Published: (2026)

An Idiosyncrasy of Time-discretization in Reinforcement Learning
by: De Asis, Kris, et al.
Published: (2024)