Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,38 @@
+---
+tags:
+  - sparse-autoencoder
+  - llava
+  - clip
+  - machine-unlearning
+  - vision-language-model
+---
+
+# Micro-SAE for LLaVA 1.5 7B Vision Tower
+
+A Sparse Autoencoder trained on CLIP ViT-L/14 patch activations (Layer 23)
+extracted from `llava-hf/llava-1.5-7b-hf`.
+
+## Architecture
+- **Input dim**: 1024 (CLIP ViT-L/14 hidden size)
+- **Dictionary size**: 4096 (4× expansion)
+- **Activation**: ReLU + L1
+
+## Usage
+
+```python
+import torch
+import json
+
+# Load config
+with open("config.json") as f:
+    config = json.load(f)
+
+# Recreate and load SAE
+sae = SparseAutoencoder(config["input_dim"], config["dict_size"])
+sae.load_state_dict(torch.load("micro_sae_1024d.pt"))
+```
+
+## Training Data
+- 20,000 COCO images
+- 500 zebra images (concept-specific)
+- 500 fire-truck images (concept-specific)