WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.
arXiv preprint arXiv:2410.06672 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Introduces source-control certificates with Type-I guarantees and a sample-complexity bound for auditing clean-source activation patches on Qwen2.5-7B and Llama3-8B for GSM8K/MATH-500 CoT hijacks.
citing papers explorer
-
WriteSAE: Sparse Autoencoders for Recurrent State
WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.
-
Auditing CoT Answer-Hijack Patches: Source-Control Certificates with Type-I Guarantees
Introduces source-control certificates with Type-I guarantees and a sample-complexity bound for auditing clean-source activation patches on Qwen2.5-7B and Llama3-8B for GSM8K/MATH-500 CoT hijacks.