interpretability-jam
There are 4 repositories under interpretability-jam topic.
apartresearch/interpretability-starter
🧠 Starter templates for doing interpretability research
poppingtonic/transformer-visualization
Mechanistic Interpretability Tutorials, Results and research log as I learn from publicly available research, and experimentation.
apartresearch/deepdecipher
🦠 DeepDecipher: An open source API to MLP neurons
McHughes288/whisper_logit_lens
This Alignment Jam Hackathon project explores whether the concept of "logit lens" applies to the encoder and decoder layers in Whisper, an end-to-end speech recognition model.