Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
imagenet-sae-top_k-64-patches_only-layer_11-hook_resid_post-128-80 – AI Model by Prisma-Multimodal | AlphaNeural AI
You can deploy this model and start earning money today!
Prisma-Multimodal
/
imagenet-sae-top_k-64-patches_only-layer_11-hook_resid_post-128-80
like
0
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
CLIP Sparse Autoencoder Checkpoint
This model is a sparse autoencoder trained on CLIP's internal representations.
Model Details
Architecture
Layer
: 11
Layer Type
: hook_resid_post
Model
: open-clip:laion/CLIP-ViT-B-32-DataComp.XL-s13B-b90K
Dictionary Size
: 49152
Input Dimension
: 768
Expansion Factor
: 64
CLS Token Only
: False
Training
Training Images
: 1299936
Learning Rate
: 0.0001
L1 Coefficient
: 0.0002
Batch Size
: 4096
Context Size
: 49
Performance Metrics
Sparsity
L0 (Active Features)
: 128.0000
Dead Features
: 0
Mean Log10 Feature Sparsity
: -2.8734
Features Below 1e-5
: 77
Features Below 1e-6
: 0
Mean Passes Since Fired
: 0.3174
Reconstruction
Explained Variance
: 0.8085
Explained Variance Std
: 0.0603
MSE Loss
: 0.0049
L1 Loss
: 0
Overall Loss
: 0.0049
Training Details
Training Duration
: 4293 seconds
Final Learning Rate
: 0.0000
Warm Up Steps
: 500
Gradient Clipping
: 1
Additional Information
Original Checkpoint Path
: /network/scratch/p/praneet.suresh/celeba_checkpoints/c08f9a92-tinyclip_sae_16_hyperparam_sweep_lr/n_images_1300020.pt
Wandb Run
:
https://wandb.ai/perceptual-alignment/imagenet-sweep-topk-patches_all_layers/runs/iefff5zu
Random Seed
: 42
