CS Researcher · ML Engineer · UW Allen School
CS student at UW researching sparse autoencoders, mechanistic interpretability, and representation geometry.
Re-Align Research Workshop
Adapting the rotation trick to TopK sparse autoencoders — rotating the k-activated subspace to preserve principal components across gradient updates, eliminating dead features entirely.
dictionary utilization vs 47% baseline
Neural architectures that respect the symmetry groups of data — SO(3), SE(3), and beyond. Equivariance as inductive bias.
Mechanistic interpretability via geometric sparsity. Recovering the true over-complete dictionary of representation space.
How CNN inductive biases shape self-supervised representation geometry — alignment, uniformity, and dimensional collapse.