Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
imagenet-sae-top_k-64-patches_only-layer_7-hook_resid_post-128-83 – 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_7-hook_resid_post-128-83
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
: 7
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
: 0.0003
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
: -2.9700
Features Below 1e-5
: 0
Features Below 1e-6
: 0
Mean Passes Since Fired
: 0.1785
Reconstruction
Explained Variance
: 0.8384
Explained Variance Std
: 0.0377
MSE Loss
: 0.0019
L1 Loss
: 0
Overall Loss
: 0.0019
Training Details
Training Duration
: 4271 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/c7b48993-tinyclip_sae_16_hyperparam_sweep_lr/n_images_1300020.pt
Wandb Run
:
https://wandb.ai/perceptual-alignment/imagenet-sweep-topk-patches_all_layers/runs/yl81cbmr
Random Seed
: 42
