Cover Image

Pairwise matrices for sparse autoencoders: single-feature inspection mislabels causal axes

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Riegler, Michael A., Torpmann-Hagen, Birk Sebastian Frostelid
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Probabilistic Runtime Verification, Evaluation and Risk Assessment of Visual Deep Learning Systems
by: Torpmann-Hagen, Birk, et al.
Published: (2025)

Defending against Stegomalware in Deep Neural Networks with Permutation Symmetry
by: Torpmann-Hagen, Birk, et al.
Published: (2025)

Understanding sparse autoencoder scaling in the presence of feature manifolds
by: Michaud, Eric J., et al.
Published: (2025)

Scaling and evaluating sparse autoencoders
by: Gao, Leo, et al.
Published: (2024)

Calibration improves detection of mislabeled examples
by: Chibane, Ilies, et al.
Published: (2025)

Decomposing multimodal embedding spaces with group-sparse autoencoders
by: Kaushik, Chiraag, et al.
Published: (2026)

When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels
by: Gautam, Sushant, et al.
Published: (2026)

Investigating task-specific prompts and sparse autoencoders for activation monitoring
by: Tillman, Henk, et al.
Published: (2025)

Applying sparse autoencoders to unlearn knowledge in language models
by: Farrell, Eoin, et al.
Published: (2024)

Asset management, condition monitoring and Digital Twins: damage detection and virtual inspection on a reinforced concrete bridge
by: Hagen, Arnulf, et al.
Published: (2024)

Steering CLIP's vision transformer with sparse autoencoders
by: Joseph, Sonia, et al.
Published: (2025)

Insights into a radiology-specialised multimodal large language model with sparse autoencoders
by: Bouzid, Kenza, et al.
Published: (2025)

Can sparse autoencoders make sense of gene expression latent variable models?
by: Schuster, Viktoria
Published: (2024)

Can sparse autoencoders be used to decompose and interpret steering vectors?
by: Mayne, Harry, et al.
Published: (2024)

Ransomware detection using stacked autoencoder for feature selection
by: Nkongolo, Mike, et al.
Published: (2024)

Transformer autoencoder with local attention for sparse and irregular time series with application on risk estimation
by: Rodis, Panteleimon
Published: (2026)

Predicted-occupancy grids for vehicle safety applications based on autoencoders and the Random Forest algorithm
by: Nadarajan, Parthasarathy, et al.
Published: (2025)

Exact discovery is polynomial for certain sparse causal Bayesian networks
by: Rios, Felix L., et al.
Published: (2024)

Position: AI Security Policy Should Target Systems, Not Models
by: Riegler, Michael A., et al.
Published: (2026)

Filtering out mislabeled training instances using black-box optimization and quantum annealing
by: Otsuka, Makoto, et al.
Published: (2025)

Why should autoencoders work?
by: Kvalheim, Matthew D., et al.
Published: (2023)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Imputation using training labels and classification via label imputation
by: Nguyen, Thu, et al.
Published: (2023)

CAVACHON: a hierarchical variational autoencoder to integrate multi-modal single-cell data
by: Hsieh, Ping-Han, et al.
Published: (2024)

Standard Acquisition Is Sufficient for Asynchronous Bayesian Optimization
by: Riegler, Ben, et al.
Published: (2026)

Bilinear autoencoders find interpretable manifolds
by: Dooms, Thomas, et al.
Published: (2026)

Matching aggregate posteriors in the variational autoencoder
by: Saha, Surojit, et al.
Published: (2023)

Slim multi-scale convolutional autoencoder-based reduced-order models for interpretable features of a complex dynamical system
by: Teutsch, Philipp, et al.
Published: (2025)

3D variational autoencoder for fingerprinting microstructure volume elements
by: White, Michael D., et al.
Published: (2025)

Model-based causal feature selection for general response types
by: Kook, Lucas, et al.
Published: (2023)

Complex variational autoencoders admit Kähler structure
by: Gracyk, Andrew
Published: (2025)

Celcomen: spatial causal disentanglement for single-cell and tissue perturbation modeling
by: Megas, Stathis, et al.
Published: (2024)

Learning low-dimensional representations of ensemble forecast fields using autoencoder-based methods
by: Chen, Jieyu, et al.
Published: (2025)

What is causal about causal models and representations?
by: Jørgensen, Frederik Hytting, et al.
Published: (2025)

Causally-Guided Pairwise Transformer -- Towards Foundational Digital Twins in Process Industry
by: Mayr, Michael, et al.
Published: (2025)

Adaptive sampling using variational autoencoder and reinforcement learning
by: Rasheed, Adil, et al.
Published: (2025)

Pairwise Markov Chains for Volatility Forecasting
by: Azeraf, Elie
Published: (2024)

Advancing sleep detection by modelling weak label sets: A novel weakly supervised learning approach
by: Boeker, Matthias, et al.
Published: (2024)

scMEDAL for the interpretable analysis of single-cell transcriptomics data with batch effect visualization using a deep mixed effects autoencoder
by: Andrade, Aixa X., et al.
Published: (2024)

Ensemble Kalman filter in latent space using a variational autoencoder pair
by: Pasmans, Ivo, et al.
Published: (2025)