AINeutralarXiv – CS AI · 5h ago6/10
🧠
Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction
Researchers applied sparse autoencoders to a clinical sequence model trained on electronic health records, revealing how the model abstracts medical information across layers. While SAE features outperformed dense representations for mortality prediction in full-sequence settings, dense representations proved superior in clinically relevant scenarios with temporal constraints, suggesting interpretability gains may not translate to practical clinical improvements.