# Sparse Autoencoders for Sequential Recommendation Models: Interpretation and Flexible Control

arXiv: https://arxiv.org/abs/2507.12202 · HTML: https://mlsanity.com/paper/2507.12202/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in SAE features and their applications, one of 13 directions in Mechanistic interpretability.
- Builds on 22 of its 51 references that are in the map.
- First posted on arXiv 16 Jul 2025.

## Placed in

- Mechanistic interpretability / [SAE features and their applications](https://mlsanity.com/mechinterp/sae-features-and-their-applications/)

## Builds on (most cited first, 22 of 22)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Emergent Linear Representations in World Models of Self-Supervised Sequence Models](https://mlsanity.com/paper/2309.00941/) (2023)
- [Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders](https://mlsanity.com/paper/2407.14435/) (2024)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](https://mlsanity.com/paper/1708.04617/) (2017)
- [An Interpretability Illusion for BERT](https://mlsanity.com/paper/2104.07143/) (2021)
- [Controllable Multi-Interest Framework for Recommendation](https://mlsanity.com/paper/2005.09347/) (2020)
- [Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control](https://mlsanity.com/paper/2405.08366/) (2024)
- [Personalized Prompt Learning for Explainable Recommendation](https://mlsanity.com/paper/2202.07371/) (2022)
- [Counterfactual Explainable Recommendation](https://mlsanity.com/paper/2108.10539/) (2021)
- [The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision](https://mlsanity.com/paper/2406.03662/) (2024)
- [Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection](https://mlsanity.com/paper/2006.10966/) (2020)
- [gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Sampling](https://mlsanity.com/paper/2308.07192/) (2023)
- [Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT](https://mlsanity.com/paper/2402.12201/) (2024)
- [Aligning Large Language Models for Controllable Recommendations](https://mlsanity.com/paper/2403.05063/) (2024)
- [Editable User Profiles for Controllable Text Recommendation](https://mlsanity.com/paper/2304.04250/) (2023)
- [Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs](https://mlsanity.com/paper/2409.18721/) (2024)
- [The Future is Sparse: Embedding Compression for Scalable Retrieval in Recommender Systems](https://mlsanity.com/paper/2505.11388/) (2025)
- [RePlay: a Recommendation Framework for Experimentation and Production Use](https://mlsanity.com/paper/2409.07272/) (2024)

## Built on by (most cited first, 2 of 2)

- [Adaptive Weighted Loss for Sequential Recommendations on Sparse Domains](https://mlsanity.com/paper/2510.04375/) (2025)
- [SAERec: Constructing Fine-grained Interpretable Intents Priors via Sparse Autoencoders for Recommendation](https://mlsanity.com/paper/2606.18897/) (2026)

## Abstract (arXiv)

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their internals can help understand, influence, and control their behavior, which is very important in a variety of real-world applications. Recently, sparse autoencoders (SAE) have been shown to be a promising unsupervised approach to extract interpretable features from neural networks. In this work, we extend SAE to sequential recommender systems and propose a framework for interpreting and controlling model representations. We show that this approach can be successfully applied to the transformer trained on a sequential recommendation task: directions learned in such an unsupervised regime turn out to be more interpretable and monosemantic than the original hidden state dimensions. Further, we demonstrate a straightforward way to effectively and flexibly control the model's behavior, giving developers and users of recommendation systems the ability to adjust their recommendations to various custom scenarios and contexts.