Author

K. Tou

h-index 0 View on Semantic Scholar

We have 1 of 2 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.

Jul 2026

Scaling Interpretable Transformers with Parity Bottleneck Layers

The ParityTransformer is introduced, a GPT-2-scale architecture whose intermediate representations are efficient and wide / sparse by design, and seen as a step toward training models whose internal representations are interpretable by design rather than recovered post hoc.

Andrew Mack, K. Tou, Mark C. Henry et al. · arXiv.org · 0 citations