sparse-autoencoder-clip-b-32-sae-vanilla-x64-layer-11-hook_resid_post

CLIP-B-32 Sparse Autoencoder x64 vanilla - L1:8e-05

Training Details

• Base Model: CLIP-ViT-B-32 (LAION DataComp.XL-s13B-b90K)
• Layer: 11
• Component: hook_resid_post

Model Architecture

• Input Dimension: 768
• SAE Dimension: 49,152
• Expansion Factor: x64 (vanilla architecture)
• Activation Function: ReLU
• Initialization: encoder_transpose_decoder
• Context Size: 50 tokens

Performance Metrics

• L1 Coefficient: 8e-05
• L0 Sparsity: 287.6007
• Explained Variance: 0.7931 (79.31%)

Training Configuration

• Learning Rate: 0.0004
• LR Scheduler: Cosine Annealing with Warmup (200 steps)
• Epochs: 10
• Gradient Clipping: 1.0
• Device: NVIDIA Quadro RTX 8000

Experiment Tracking:

• Weights & Biases Run ID: xwlpfrzs
• Full experiment details: https://wandb.ai/perceptual-alignment/clip/runs/xwlpfrzs/overview
• Git Commit: e22dd02726b74a054a779a4805b96059d83244aa

Citation

@misc{2024josephsparseautoencoders,
    title={Sparse Autoencoders for CLIP-ViT-B-32},
    author={Joseph, Sonia},
    year={2024},
    publisher={Prisma-Multimodal},
    url={https://huggingface.co/Prisma-Multimodal},
    note={Layer 11, hook_resid_post, Run ID: xwlpfrzs}
}