pith. sign in

Transformer Circuits Thread , year =

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

years

2026 2

representative citing papers

Geometric Factual Recall in Transformers

cs.CL · 2026-05-12 · conditional · novelty 8.0

A single-layer transformer memorizes random subject-attribute bijections using logarithmic embedding dimension via linear superpositions in embeddings and ReLU-gated selection in the MLP, with zero-shot transfer to new facts and matching multi-hop constructions.

Asymmetric Scaling Laws from Sparse Features

stat.ML · 2026-05-22 · unverdicted · novelty 5.0

A sparse-activation model predicts double-descent loss with distinct under- and over-parameterized scaling exponents set by sparsity, plus a compute-optimal frontier favoring dataset growth.

citing papers explorer

Showing 2 of 2 citing papers.

  • Geometric Factual Recall in Transformers cs.CL · 2026-05-12 · conditional · none · ref 24

    A single-layer transformer memorizes random subject-attribute bijections using logarithmic embedding dimension via linear superpositions in embeddings and ReLU-gated selection in the MLP, with zero-shot transfer to new facts and matching multi-hop constructions.

  • Asymmetric Scaling Laws from Sparse Features stat.ML · 2026-05-22 · unverdicted · none · ref 59

    A sparse-activation model predicts double-descent loss with distinct under- and over-parameterized scaling exponents set by sparsity, plus a compute-optimal frontier favoring dataset growth.