Saved in:
Bibliographic Details
Main Authors: Spišák, Martin, Peška, Ladislav, Škoda, Petr, Vančura, Vojtěch, Alves, Rodrigo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.11182
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917206346956800
author Spišák, Martin
Peška, Ladislav
Škoda, Petr
Vančura, Vojtěch
Alves, Rodrigo
author_facet Spišák, Martin
Peška, Ladislav
Škoda, Petr
Vančura, Vojtěch
Alves, Rodrigo
contents Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the generation process by selectively activating specific neurons in their latent activations. Our paper is the first to apply this approach to collaborative filtering, aiming to extract similarly interpretable features from representations learned purely from interaction signals. In particular, we focus on a widely adopted class of collaborative autoencoders (CFAEs) and augment them by inserting an SAE between their encoder and decoder networks. We demonstrate that such representation is largely monosemantic and propose suitable mapping functions between semantic concepts and individual neurons. We also evaluate a simple yet effective method that utilizes this representation to steer the recommendations in a desired direction.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11182
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Knots to Knobs: Towards Steerable Collaborative Filtering Using Sparse Autoencoders
Spišák, Martin
Peška, Ladislav
Škoda, Petr
Vančura, Vojtěch
Alves, Rodrigo
Information Retrieval
Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the generation process by selectively activating specific neurons in their latent activations. Our paper is the first to apply this approach to collaborative filtering, aiming to extract similarly interpretable features from representations learned purely from interaction signals. In particular, we focus on a widely adopted class of collaborative autoencoders (CFAEs) and augment them by inserting an SAE between their encoder and decoder networks. We demonstrate that such representation is largely monosemantic and propose suitable mapping functions between semantic concepts and individual neurons. We also evaluate a simple yet effective method that utilizes this representation to steer the recommendations in a desired direction.
title From Knots to Knobs: Towards Steerable Collaborative Filtering Using Sparse Autoencoders
topic Information Retrieval
url https://arxiv.org/abs/2601.11182