R-lens: Making J-lens More Faithful on Early Layers

·LessWrong··

TL;DR:We introduce the R-lens: a drop-in replacement for J-lens that produces clearer readouts on earlier layers. We fit the R-lens on Jacobians computed through an LRP-modified backward pass, using the gradient-propagation rules from relevance patching (RelP) rather than standard gradients, which allows us to reduce the propagation of errors throughout the backwards pass. This method allows us to surface important intermediate variables more consistently and more saliently, reduce the frequency...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 6h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
Harvard researchers find AI coding agents shifted the bottleneck to code review
judahmeek · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 1d ago