2 papers
cs.LG2026
Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?
Philippe Chlenski, Zachariah Carmichael, Ayush Warikoo +5
Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens…
cs.CV2025
On Symmetries in Convolutional Weights
Bilal Alsallakh, Timothy Wroge, Vivek Miglani +1
We explore the symmetry of the mean k x k weight kernel in each layer of various convolutional neural networks. Unlike individual neurons, the mean kernels in internal layers tend…