# ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders

arXiv: https://arxiv.org/abs/2607.27404 · HTML: https://mlsanity.com/paper/2607.27404/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Concept Bottleneck Models](https://mlsanity.com/paper/2007.04612/) (2020)
- [Interpretable machine learning: definitions, methods, and applications](https://mlsanity.com/paper/1901.04592/) (2019)
- [LEACE: Perfect linear concept erasure in closed form](https://mlsanity.com/paper/2306.03819/) (2023)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Automatic diagnosis of the 12-lead ECG using a deep neural network](https://mlsanity.com/paper/1904.01949/) (2019)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use](https://mlsanity.com/paper/1905.05134/) (2019)
- [ECG-FM: An Open Electrocardiogram Foundation Model](https://mlsanity.com/paper/2408.05178/) (2024)
- [Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control](https://mlsanity.com/paper/2405.08366/) (2024)
- [Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram](https://mlsanity.com/paper/2402.09450/) (2024)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2412.12101/) (2024)
- [Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations](https://mlsanity.com/paper/2103.01890/) (2021)
- [Learning General Representation of 12-Lead Electrocardiogram with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2410.08559/) (2024)
- [Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders](https://mlsanity.com/paper/2605.13930/) (2026)

## Abstract (arXiv)

Existing benchmarks for electrocardiogram foundation models primarily evaluate downstream predictive performance, providing limited insight into whether their internal representations can be faithfully decomposed, clinically interpreted, or reproduced across independent analyses. We introduce ECG-InterpBench, a benchmark designed to systematically evaluate the interpretability of ECG foundation-model representations. ECG-InterpBench uses sparse autoencoders as standardized measurement instruments and matches their capacity across models to enable controlled comparisons. We evaluate six frozen ECG foundation models across five standardized encoder depths, five matched dictionary widths, and three random seeds, producing a 450-cell interpretability atlas comprising 75 exactly matched six-model comparison blocks. The benchmark evaluates complementary dimensions of representation interpretability, including sparse reconstruction fidelity, single-feature accessibility and coverage of 49 clinically meaningful ECG measurements, and cross-seed feature reproducibility. The evaluation further quantifies patient-sampling uncertainty, depth- and seed-dependent variation, and sensitivity to the sparsity parameterization. The benchmark reveals that ECG foundation models exhibit distinct interpretability profiles. A matched replication on MIMIC-IV-ECG confirms that reconstruction fidelity and clinical accessibility identify different leading models. The benchmark is accompanied by executable evaluation code, standardized manifests, cell-level metrics, and reproducibility audits. ECG-InterpBench complements performance-centered ECG benchmarks by providing a capacity-controlled and reproducible framework for comparing ECG foundation models across distinct dimensions of representation interpretability.