Cover Image

Superposition disentanglement of neural representations reveals hidden alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Longon, André, Klindt, David, Khosla, Meenakshi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Measuring the Representational Alignment of Neural Systems in Superposition
by: Liu, Sunny, et al.
Published: (2026)

Barycentric alignment for instance-level comparison of neural representations
by: Saha, Shreya, et al.
Published: (2026)

Sparse components distinguish visual pathways & their alignment to neural networks
by: Marvi, Ammar I, et al.
Published: (2025)

Naturally Computed Scale Invariance in the Residual Stream of ResNet18
by: Longon, André
Published: (2025)

Interpreting the Residual Stream of ResNet18
by: Longon, André
Published: (2024)

From superposition to sparse codes: interpretable representations in neural networks
by: Klindt, David, et al.
Published: (2025)

Representational Alignment Across Model Layers and Brain Regions with Multi-Level Optimal Transport
by: Shah, Shaan, et al.
Published: (2025)

Modeling the language cortex with form-independent and enriched representations of sentence meaning reveals remarkable semantic abstractness
by: Saha, Shreya, et al.
Published: (2025)

Modeling the Human Visual System: Comparative Insights from Response-Optimized and Task-Optimized Vision Models, Language Models, and different Readout Mechanisms
by: Saha, Shreya, et al.
Published: (2024)

Uncovering hidden geometry in Transformers via disentangling position and context
by: Song, Jiajun, et al.
Published: (2023)

Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence
by: Kapoor, Chaitanya, et al.
Published: (2026)

IndiSeek learns information-guided disentangled representations
by: Gui, Yu, et al.
Published: (2025)

Data Whitening Improves Sparse Autoencoder Learning
by: Saraswatula, Ashwin, et al.
Published: (2025)

Sparsity regularization via tree-structured environments for disentangled representations
by: Layne, Elliot, et al.
Published: (2024)

Human alignment of neural network representations
by: Muttenthaler, Lukas, et al.
Published: (2022)

Measuring the Measures: Discriminative Capacity of Representational Similarity Metrics Across Model Families
by: Wu, Jialin, et al.
Published: (2025)

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
by: O'Neill, Charles, et al.
Published: (2024)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
by: Ibrahim, Mark, et al.
Published: (2024)

Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning
by: Gutheil, Julian, et al.
Published: (2026)

How does Graph Structure Modulate Membership-Inference Risk for Graph Neural Networks?
by: Khosla, Megha
Published: (2026)

Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
by: Kunin, Daniel, et al.
Published: (2024)

Variational decomposition autoencoding improves disentanglement of latent representations
by: Ziogas, Ioannis, et al.
Published: (2026)

Disentangled and Self-Explainable Node Representation Learning
by: Piaggesi, Simone, et al.
Published: (2024)

Dimensions underlying the representational alignment of deep neural networks with humans
by: Mahner, Florian P., et al.
Published: (2024)

Getting aligned on representational alignment
by: Sucholutsky, Ilia, et al.
Published: (2023)

Brain-Model Evaluations Need the NeuroAI Turing Test
by: Feather, Jenelle, et al.
Published: (2025)

GNN-MultiFix: Addressing the pitfalls for GNNs for multi-label node classification
by: Zhao, Tianqi, et al.
Published: (2024)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
by: Reizinger, Patrik, et al.
Published: (2025)

Transferring disentangled representations: bridging the gap between synthetic and real images
by: Dapueto, Jacopo, et al.
Published: (2024)

Are aligned neural networks adversarially aligned?
by: Carlini, Nicholas, et al.
Published: (2023)

An unsupervised tour through the hidden pathways of deep neural networks
by: Doimo, Diego
Published: (2025)

Evaluating alignment between humans and neural network representations in image-based learning tasks
by: Demircan, Can, et al.
Published: (2023)

Latent Functional Maps: a spectral framework for representation alignment
by: Fumero, Marco, et al.
Published: (2024)

Enforcing hidden physics in physics-informed neural networks
by: Chen, Nanxi, et al.
Published: (2025)

Adversarial Examples Are Not Bugs, They Are Superposition
by: Gorton, Liv, et al.
Published: (2025)

Inference of hidden common driver dynamics by anisotropic self-organizing neural networks
by: Benkő, Zsigmond, et al.
Published: (2025)

Knowledge distillation through geometry-aware representational alignment
by: Bhattarai, Prajjwal, et al.
Published: (2025)

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
by: Pacela, Vitória Barin, et al.
Published: (2026)

Causality is Key for Interpretability Claims to Generalise
by: Joshi, Shruti, et al.
Published: (2026)

Draw a Portrait of Your Graph Data: An Instance-Level Profiling Framework for Graph-Structured Data
by: Zhao, Tianqi, et al.
Published: (2025)