Prisma-Multimodal/DINO-vanilla-x64-all_patches_8-resid_post-530-90

Model

0

stars

5

commits

5

linked in READMEs

Apr 18, 2025

updated

Browse cluster: Self-Supervised Vision Model Training →

README

DINO Sparse Autoencoder Checkpoint

This model is a sparse autoencoder trained on DINO's internal representations.

Model Details

Architecture

Layer: 8
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: 0.01978789319686339
Batch Size: 4096
Context Size: 197

Sparsity

L0 (Active Features): 530

Additional Information

Wandb Run: https://wandb.ai/perceptual-alignment/DINO-SAE-Vanilla-Sweep/runs/z7rto0ct/
Random Seed: 42

Contributors

5 commits

Similar repos

Prisma-Multimodal/DINO-vanilla-x64-all_patches_0-resid_post-507-98

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_1-resid_post-549-95

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_3-resid_post-989-95

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_4-resid_post-876-99

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_2-resid_post-661-95

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_9-resid_post-1105-99

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_10-resid_post-835-99

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_7-resid_post-1086-98

0

Linked in READMEs

Prisma-Multimodal/ViT-Prisma

ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).

388

soniajoseph/ViT-Prisma

ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).

388

leeloolee/df-prisma

0

natihash/my_prisma

0

alexlav17/ViT-Prisma-fix

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_8-resid_post-530-90

Model

0

stars

5

commits

5

linked in READMEs

Apr 18, 2025

updated

Browse cluster: Self-Supervised Vision Model Training →

README

DINO Sparse Autoencoder Checkpoint

This model is a sparse autoencoder trained on DINO's internal representations.

Model Details

Architecture

Layer: 8
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: 0.01978789319686339
Batch Size: 4096
Context Size: 197

Sparsity

L0 (Active Features): 530

Additional Information

Wandb Run: https://wandb.ai/perceptual-alignment/DINO-SAE-Vanilla-Sweep/runs/z7rto0ct/
Random Seed: 42

Similar repos

Prisma-Multimodal/DINO-vanilla-x64-all_patches_0-resid_post-507-98

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_1-resid_post-549-95

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_3-resid_post-989-95

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_4-resid_post-876-99

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_2-resid_post-661-95

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_9-resid_post-1105-99

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_10-resid_post-835-99

0

Prisma-Multimodal/DINO-vanilla-x64-all_patches_7-resid_post-1086-98

0

Linked in READMEs

Prisma-Multimodal/ViT-Prisma

ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).

388

soniajoseph/ViT-Prisma

ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).

388

leeloolee/df-prisma

0

natihash/my_prisma

0

alexlav17/ViT-Prisma-fix

0

Contributors

5 commits