Pith. sign in

Sparsity in transformers: A systematic literature review

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

TopK Language Models

cs.CL · 2025-06-26 · conditional · novelty 6.0

A transformer LM trained with TopK activations in its hidden layers produces sparse, SAE-like internal representations without needing post-hoc sparse autoencoder training.

citing papers explorer

Showing 1 of 1 citing paper.

  • TopK Language Models cs.CL · 2025-06-26 · conditional · none · ref 7

    A transformer LM trained with TopK activations in its hidden layers produces sparse, SAE-like internal representations without needing post-hoc sparse autoencoder training.