4 papers
The Birth of Knowledge: Emergent Features across Time, Space, and Scale in Large Language Models
Shashata Sawmya, Micah Adler, Nir Shavit
This paper studies the emergence of interpretable categorical features within large language models (LLMs), analyzing their behavior across training checkpoints (time), transformer…
Cascade Detector Analysis and Application to Biomedical Microscopy
Thomas L. Athey, Shashata Sawmya, Nir Shavit
As both computer vision models and biomedical datasets grow in size, there is an increasing need for efficient inference algorithms. We utilize cascade detectors to efficiently ide…
NeuroADDA: Active Discriminative Domain Adaptation in Connectomic
Shashata Sawmya, Thomas L. Athey, Gwyneth Liu +1
Training segmentation models from scratch has been the standard approach for new electron microscopy connectomics datasets. However, leveraging pretrained models from existing data…
Wasserstein Distances, Neuronal Entanglement, and Sparsity
Shashata Sawmya, Linghao Kong, Ilia Markov +2
Disentangling polysemantic neurons is at the core of many current approaches to interpretability of large language models. Here we attempt to study how disentanglement can be used…