CLIP-featurevis
CLIP-featurevis copied to clipboard
code for reproducing some of the diagrams in the paper "Multimodal Neurons in Artificial Neural Networks"
Results
4
CLIP-featurevis issues
Sort by
recently updated
recently updated
newest added
Imagen' key discovery is that generic large language models (e.g. T5), pretrained on text-only corpora, are surprisingly effective at encoding text for image synthesis: increasing the size of the language...
Dear OpenAI team, Thank you for sharing this great implementation, I really kile it. In the section 'Understanding Language', you mention about: ``` If we fix a neuron on the...
Colab?
7
Can someone make a colab notebook for this?