4 papers
Neuron Populations Exhibit Divergent Selectivity with Scale
Amil Dravid, Yasaman Bahri, Alexei A. Efros +1
We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as loss. To probe this qu…
Caption-Driven Explainability: Probing CNNs for Bias via CLIP
Patrick Koller, Amil V. Dravid, Guido M. Schuster +1
Robustness has become one of the most critical problems in machine learning (ML). The science of interpreting ML models to understand their behavior and improve their robustness is…
Vision Transformers Don't Need Trained Registers
Nick Jiang, Amil Dravid, Alexei Efros +1
We investigate the mechanism underlying a previously identified phenomenon in Vision Transformers - the emergence of high-norm tokens that lead to noisy attention maps (Darcet et a…
Interpreting the Weight Space of Customized Diffusion Models
Amil Dravid, Yossi Gandelsman, Kuan-Chieh Wang +4
We investigate the space of weights spanned by a large collection of customized diffusion models. We populate this space by creating a dataset of over 60,000 models, each of which…