[Linkpost] Interpreting Language Model Parameters

·LessWrong··

This is the latest work in our Parameter Decomposition agenda. We introduce a new parameter decomposition method, adVersarial Parameter Decomposition (VPD)[1] and decompose the parameters of a small[2] language model with it. VPD greatly improves on our previous techniques, Stochastic Parameter Decomposition (SPD) and Attribution-based Parameter Decomposition (APD). We think the parameter decomposition approach is now more-or-less ready to be applied at scale to models people care about.Importan...

Read full article →

Related Articles

A circuit prior in NN-bayes
Kaarel · LessWrong · 57m ago
MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 1mo ago
Item Response Theory for AI Safety
Joshua Fonseca Rivera · LessWrong · 12d ago
An OpenAI model left notes about how to evade containment
Alex Mallen · Redwood Research · 24d ago
The OpenAI models that hacked Hugging Face weren’t just following instructions
Girish Gupta · Redwood Research · 24d ago