PraneetNeuro's picture
Update README.md
36e70dd verified
# DINO Sparse Autoencoder Checkpoint
This model is a sparse autoencoder trained on DINO's internal representations.
## Model Details
### Architecture
- **Layer**: 2
- **Layer Type**: hook_resid_post
- **Model**: facebook/vitb-16
- **Dictionary Size**: 49152
- **Input Dimension**: 768
- **Expansion Factor**: 64
- **CLS Token Only**: False
### Training
- **Learning Rate**: 0.0061296854816475805
- **Batch Size**: 4096
- **Context Size**: 197
### Sparsity
- **L0 (Active Features)**: 661
## Additional Information
- **Wandb Run**: https://wandb.ai/perceptual-alignment/DINO-SAE-Vanilla-Sweep/runs/6bdgu49a/
- **Random Seed**: 42