CLIP-featurevis icon indicating copy to clipboard operation
CLIP-featurevis copied to clipboard

Published 20 hours ago • verified publisher icon openai
→

Metadata

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

try to visualize the features of T5: Text-To-Text Transfer Transformer?

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...

Wulx2050 avatar Wulx2050

text feature visualization

4 comment

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...

betterze avatar betterze

Colab?

7 comment

Can someone make a colab notebook for this?

Devetec avatar Devetec

Create README.md

scriptkkiddie avatar scriptkkiddie

← Metadata

300
Stars
75
Forks
Watchers

Owner

verified publisher icon openai

Metadata

code for reproducing some of the diagrams in the paper "Multimodal Neurons in Artificial Neural Networks"

Back