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-9-hook_mlp_out-l1-8e-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-9-hook_mlp_out-l1-8e-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-9-hook_mlp_out-l1-8e-05")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Prisma-Multimodal/sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-9-hook_mlp_out-l1-8e-05", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload SAE model
Browse files- n_images_2600058.pt +3 -0
n_images_2600058.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18f0280cc390a280adb458b2b5b0b7837a4693de2c5a9dc852c529aeac7e0d21
|
| 3 |
+
size 302191832
|