Feature Extraction
Transformers
English
torch
clip
vision
interpretability
sparse autoencoder
sae
mechanistic interpretability
Instructions to use Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-3-hook_resid_post-l1-1e-05 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-3-hook_resid_post-l1-1e-05 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-3-hook_resid_post-l1-1e-05")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-3-hook_resid_post-l1-1e-05", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 1179a8f246be225aff41738bb3dd33707eea24754889fa40386d928e8a52c6d3
- Size of remote file:
- 302 MB
- SHA256:
- 400b7f9f3fea4fc709863de42ae88b1596b88d4617209c130d5431da5f92f484
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.