pith. sign in

Language models can explain neurons in language models

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

1 Pith paper citing it

fields

q-bio.NC 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Features have life history. And we should care

q-bio.NC · 2026-05-07 · unverdicted · novelty 5.0

Language model features form an early stable carrier scaffold of about 50 sparse features that is load-bearing, predictable from onset firing, and recruits most later features.

citing papers explorer

Showing 1 of 1 citing paper.

  • Features have life history. And we should care q-bio.NC · 2026-05-07 · unverdicted · none · ref 22

    Language model features form an early stable carrier scaffold of about 50 sparse features that is load-bearing, predictable from onset firing, and recruits most later features.