A toy model learns a dense binary-weighted circuit for the Universal-AND problem, which outperforms prior sparse constructions at low sparsity.
What’s up with llms representing xors of arbitrary features? https://www.lesswrong.com/posts/hjJXCn9GsskysDceS/what-s-up-with-llms-representing-xors-of-arbitrary-features, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Compressed Computation: Dense Circuits in a Toy Model of the Universal-AND Problem
A toy model learns a dense binary-weighted circuit for the Universal-AND problem, which outperforms prior sparse constructions at low sparsity.