other

J-lens (Jacobian lens)

An interpretability readout that maps intermediate-layer activations into vocabulary space using the Jacobian from that layer to the final residual stream, averaged over prompts and token positions.

Known aliases

Jacobian lens
J-space lens

Relationships

No evidence-backed relationships are recorded.

Current clusters

build1 publisher

A 4B model learned two-hop geography with its top J-lens directions suppressed all through training

In a single-author LessWrong experiment, accuracy on held-out countries went from 20.9% to 97.7% with the lesion active in every forward pass, and the recovery survived refitting the lens to the adapted model.

Publishers:lesswrong.com

Reality

Evidence34
Adoption12
Hype gap+22
Incentives18
Confidence42