Author

Philip T. H. Lee

h-index 1 View on Semantic Scholar

We have 1 of 3 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

SpIn-ViT: Designing a Sparsity-Induced Vision Transformer That Is Mechanistically Interpretable

This work introduces SpIn-ViT, a framework that jointly trains a pretrained ViT and a modified SAE end-to-end, directly aligning sparse patch-level representations with image classification, and extracts interpretable rule-sets using the SAE neurons to create neurosymbolic models.

Philip T. H. Lee, Parth Padalkar · 0 citations