tuned-lens
Tools for understanding how transformer predictions are built layer-by-layer
Explore how predictions are made in transformer models by analyzing their layers.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeTools for understanding how transformer predictions are built layer-by-layer
tuned-lens has 603 stars on GitHub. It has been forked 72 times. tuned-lens is written mainly in Python. It has been in active development since 2022. tuned-lens is available under the MIT license. Its main topics are machine-learning, pytorch, transformers.
What is tuned-lens?
Tools for understanding how transformer predictions are built layer-by-layer
Is tuned-lens open source?
tuned-lens is an open-source project. It is released under the MIT license.
Is tuned-lens free?
Yes. tuned-lens is free and open source — you can use, modify and self-host it.
What license does tuned-lens use?
tuned-lens is available under the MIT license.
What language is tuned-lens written in?
tuned-lens is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/alignmentresearch-tuned-lens.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.