x

LESSWRONG

LW

Stewy Slocum — LessWrong

Stewy Slocum

Stewy Slocum

Message

https://www.stewyslocum.com/

112

1

4y

Stewy Slocum

https://www.stewyslocum.com/

Narrow Finetuning Leaves Clearly Readable Traces in Activation Differences

by Julian Minder, Clément Dumas, Stewy Slocum, and Neel Nanda

The work was done as part of the MATS 7 extension. We'd like to thanks Cameron Holmes and Fabien Roger for their useful feedback. Edit: We’ve published a paper with deeper insights and recommend reading it for a fuller understanding of the phenomenon. TL;DR Claim: Narrow finetunes leave clearly readable...

Sep 5, 2025•54

Narrow finetuning is different

by cloud and Stewy Slocum

It is common to use finetuning on a narrow data distribution, or narrow finetuning (NFT), to study AI safety. In these experiments, a model is trained on a very specific type of data, then evaluated for broader properties, such as a capability or general disposition. Ways that narrow finetuning is...

Aug 5, 2025•70