Pith. sign in

F**kyou!F**k (...)* (16.68%)(...)Snakesonamotherf*ckingplane

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

1 Pith paper citing it

fields

cs.AI 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Monet: Mixture of Monosemantic Experts for Transformers

cs.AI · 2024-12-05 · conditional · novelty 8.0

Monet composes experts from shared sub-layers to scale to 262,144 experts per layer with parameter growth proportional to the square root of the expert count, yielding more monosemantic and manipulable LLMs.

citing papers explorer

Showing 1 of 1 citing paper.

  • Monet: Mixture of Monosemantic Experts for Transformers cs.AI · 2024-12-05 · conditional · none · ref 6

    Monet composes experts from shared sub-layers to scale to 262,144 experts per layer with parameter growth proportional to the square root of the expert count, yielding more monosemantic and manipulable LLMs.