An implementation of the template lens from appendix A.9.1 of Gurnee et al. (2026), Verbalizable Representations Form a Global Workspace in Language Models (transformer-circuits.pub, The template lens reads a residual-stream direction against a vocabulary of whole words rather than single tokens, which is what lets it name concepts the logit lens and J-lens can only show as fragments — blackmail instead of black, Equestrian instead of E/quest/rian. For a word w at layer l, collect passages each ending at the exact point where w would naturally come next, run the model over them, and average the residual stream at the final position to get muw(l). Then centre and whiten: tw is the linear…
Independent publisher
Andy Xu
andyx10
Models in Library1
Datasets in Library0
Models on Hugging Face10
Followers1
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: mit. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.