Update README.md

README.md

@@ -1,3 +1,47 @@
----
-license: cc-by-sa-4.0
----
+---
+license: cc-by-sa-4.0
+---
+# 🧠 Top-K 300 Sparse Autoencoder (SAE) — SAEdit  
+**Repo:** `Ronenk94/T5_matryoshka_sae`  
+**Model Type:** Sparse Autoencoder over T5 Embeddings  
+**Paper:** *SAEdit: Token-level control for continuous image editing via Sparse AutoEncoder*  
+**License:** CC BY 4.0
+
+---
+
+## 📌 Model Overview
+
+This repository contains the **Top-K 300 Sparse Autoencoder (SAE)** used in the SAEdit framework.  
+It is trained on **T5 text embeddings** and designed to produce **sparse latent representations** that enable *token-level semantic control* in image editing pipelines.
+
+| Property | Details |
+|----------|--------|
+| **Architecture** | GlobalBatchTopKMatryoshkaSAE |
+| **Latent sparsity** | Top-K = 300 activations |
+| **Backbone embeddings** | Frozen T5 encoder |
+| **Task** | Semantic factorization + reconstruction |
+| **Use case** | Editing directions for diffusion-based image manipulation |
+
+---
+
+## 📥 How to Load
+
+```python
+import torch
+from src.models.sparse_autoencoders.matryoshka_sae import GlobalBatchTopKMatryoshkaSAE
+
+# Option A — using a from_pretrained method (if implemented)
+model = GlobalBatchTopKMatryoshkaSAE.from_pretrained(
+    "Ronenk94/T5_matryoshka_sae",
+    device="cuda"
+)
+
+# Option B — manual load if using state_dict
+checkpoint = torch.load("pytorch_model.bin", map_location="cpu")
+with open("config.json", "r") as f:
+    cfg = json.load(f)
+
+model = GlobalBatchTopKMatryoshkaSAE(cfg)
+model.load_state_dict(checkpoint)
+model.to("cuda").eval()
+