Downloads · 30 days
8
38% of all-time downloads
sae-relu-layer_11_resid_post_IMGNET-PT_WATERBIRDS-FT
Prisma-Multimodal/sae-relu-layer_11_resid_post_IMGNET-PT_WATERBIRDS-FT
sae-relu-layer_11_resid_post_IMGNET-PT_WATERBIRDS-FT is a machine learning model from Prisma-Multimodal. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model is a sparse autoencoder trained on CLIP's internal representations. Pretrained on Imagenet and Finetuned on Waterbirds
All-time downloads
21
Public
Repo size
302 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt302 MB · 100%
At a glance
- Access
- Public
- Created
- Dec 6, 2024
- Updated
- Dec 6, 2024
- SHA
- 928907d0
Model card
From the Hugging Face model README
CLIP Sparse Autoencoder Checkpoint
Model Overview
This model is a sparse autoencoder trained on CLIP's internal representations. Pretrained on Imagenet and Finetuned on Waterbirds
Architecture Details
- Layer: 11
- Layer Type: hook_resid_post
- Model: open-clip:laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
- Dictionary Size: 49,152
- Input Dimension: 768
- Expansion Factor: 64
- CLS Token Only: False
Performance Metrics
The model has been evaluated on standard metrics with the following results:
- L0: 359
- Explained Variance: 0.85
- MSE Loss: 0.003
- Overall Loss: 0.008
Additional Information
Detailed logs and visualizations of the model's fine-tuning process are available on Weights & Biases:
wandb.ai/perceptual-alignment/waterbirds-finetuning-sweep/runs/cxgrs9zt/workspace
Feel free to reach out for any additional clarifications or details!
- Created
- Dec 6, 2024
- Updated
- Dec 6, 2024