# Learning biologically relevant features in a pathology foundation model using sparse autoencoders

arXiv: https://arxiv.org/abs/2407.10785 · HTML: https://mlsanity.com/paper/2407.10785/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Interpreting biomedical and science models, one of 13 directions in Mechanistic interpretability.
- Builds on 17 of its 40 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## Placed in

- Mechanistic interpretability / [Interpreting biomedical and science models](https://mlsanity.com/mechinterp/interpreting-biomedical-and-science-models/)

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [Progress measures for grokking via mechanistic interpretability](https://mlsanity.com/paper/2301.05217/) (2023)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias](https://mlsanity.com/paper/2004.12265/) (2020)
- [Improving Dictionary Learning with Gated Sparse Autoencoders](https://mlsanity.com/paper/2404.16014/) (2024)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [A Toy Model of Universality: Reverse Engineering How Networks Learn Group Operations](https://mlsanity.com/paper/2302.03025/) (2023)
- [Deep Learning for Identifying Metastatic Breast Cancer](https://mlsanity.com/paper/1606.05718/) (2016)
- [Automated Gleason Grading of Prostate Biopsies using Deep Learning](https://mlsanity.com/paper/1907.07980/) (2019)
- [Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology](https://mlsanity.com/paper/2206.01794/) (2022)
- [The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision](https://mlsanity.com/paper/2406.03662/) (2024)

## Built on by (most cited first, 14 of 14)

- [Understanding the Repeat Curse in Large Language Models from a Feature Perspective](https://mlsanity.com/paper/2504.14218/) (2025)
- [An X-Ray Is Worth 15 Features: Sparse Autoencoders for Interpretable Radiology Report Generation](https://mlsanity.com/paper/2410.03334/) (2024)
- [CytoSAE: Interpretable Cell Embeddings for Hematology](https://mlsanity.com/paper/2507.12464/) (2025)
- [Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation](https://mlsanity.com/paper/2603.28744/) (2026)
- [Evaluating SAE interpretability without explanations](https://mlsanity.com/paper/2507.08473/) (2025)
- [Prototype-Based Multiple Instance Learning for Gigapixel Whole Slide Image Classification](https://mlsanity.com/paper/2503.08384/) (2025)
- [Insights into a radiology-specialised multimodal large language model with sparse autoencoders](https://mlsanity.com/paper/2507.12950/) (2025)
- [Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models](https://mlsanity.com/paper/2510.25807/) (2025)
- [MedSAE: Dissecting MedCLIP Representations with Sparse Autoencoders](https://mlsanity.com/paper/2510.26411/) (2025)
- [GeoSAE: Geometric Prior-Guided Layer-Wise Sparse Autoencoder Annotation of Brain MRI Foundation Models](https://mlsanity.com/paper/2605.01829/) (2026)
- [Explainable histomorphology-based survival prediction of glioblastoma, IDH-wildtype](https://mlsanity.com/paper/2601.11691/) (2026)
- [Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction](https://mlsanity.com/paper/2605.04072/) (2026)
- [Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Concepts](https://mlsanity.com/paper/2609.08879/) (2026)
- [Latent Inference-Time Guidance of Time Series Foundation Models](https://mlsanity.com/paper/2609.38058/) (2026)

## Abstract (arXiv)

Pathology plays an important role in disease diagnosis, treatment decision-making and drug development. Previous works on interpretability for machine learning models on pathology images have revolved around methods such as attention value visualization and deriving human-interpretable features from model heatmaps. Mechanistic interpretability is an emerging area of model interpretability that focuses on reverse-engineering neural networks. Sparse Autoencoders (SAEs) have emerged as a promising direction in terms of extracting monosemantic features from polysemantic model activations. In this work, we trained a Sparse Autoencoder on the embeddings of a pathology pretrained foundation model. We found that Sparse Autoencoder features represent interpretable and monosemantic biological concepts. In particular, individual SAE dimensions showed strong correlations with cell type counts such as plasma cells and lymphocytes. These biological representations were unique to the pathology pretrained model and were not found in a self-supervised model pretrained on natural images. We demonstrated that such biologically-grounded monosemantic representations evolved across the model's depth, and the pathology foundation model eventually gained robustness to non-biological factors such as scanner type. The emergence of biologically relevant SAE features was generalizable to an out-of-domain dataset. Our work paves the way for further exploration around interpretable feature dimensions and their utility for medical and clinical applications.