Understand this story
In the Fellows Program project, Kola Ayonrinde of the Anthropic interpretability team led the proposal of J++ lens, an improved version of J-lens that can replace the original method as a plug-and-play drop-in. The work clusters activations layer by layer and fits a Jacobian for each, then combines them with learned weights, while also introducing R-lens's layer-wise relevance propagation and post-hoc filtering of spurious readout tokens. The team says that in evaluations it reads out the intermediate latent variables used in the model's reasoning more reliably than J-lens and R-lens, and has released the code, the lens, and an interactive Neuronpedia demo.
AI-generated from public reports
Developments
1 confirmed developments
- Source:Anthropic：Transformer Circuits
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 30
Anthropic：Transformer CircuitsFirst-party
Anthropic's interpretability team releases J++ lens, improving the reading of concepts in the model's intermediate layers
Anthropic's interpretability team, led by Kola Ayonrinde within the Fellows Program, proposed the J++ lens, an improved version of the J-lens that can replace the original method as a plug-and-play drop-in. The J++ lens clusters activations layer by layer and fits a separate Jacobian for each, then combines them with learned weights, while also incorporating R-lens's layer-wise relevance propagation and post-hoc filtering of spurious readout tokens. The team says that in evaluations it reads out the intermediate latent variables used in the model's reasoning more reliably than the J-lens and R-lens, and has released the code, the lens, and an interactive Neuronpedia demo.