diff --git a/README.md b/README.md
index 4d171dd..35c7dc9 100644
--- a/README.md
+++ b/README.md
@@ -14,6 +14,19 @@
+
+
+
+
+
**Overcomplete** is a compact research library in Pytorch designed to study (Overcomplete)-Dictionary learning methods to extract concepts from large **Vision models**. In addition, this repository also introduces various visualization methods, attribution and metrics. However, Overcomplete emphasizes **experimentation**.
@@ -52,7 +65,7 @@ logs = train_sae(sae, dataloader, criterion, optimizer,
- Getting started: [](https://colab.research.google.com/drive/1rB71_RdmCzr50I1Ebwfq49cEqoxt1G3X?usp=drive_link)
- TopK, BatchTopK, JumpReLU, Vanilla SAE: [](https://colab.research.google.com/drive/1LeLPF_q0Jlm9qygFtZy4KyJq5UB6E71z?usp=drive_link)
-- Stable Dictionary with Archetypal-SAE: _Coming soon_
+- Stable Dictionary with Archetypal-SAE: [](https://colab.research.google.com/drive/1TmAtUhIdFGSMlDhKr2ndXGR8GU4R4aTq?usp=sharing)
- Advanced metrics to study the solution of SAE: [](https://colab.research.google.com/drive/1hGZst7AfuxreXAOxLgJS5BtbXsdNGH09?usp=drive_link)
- The visualization module: [](https://colab.research.google.com/drive/1VWwOxyW8SVDX1_jM9AoDAjw91le_JPla?usp=sharing)
- NMF, ConvexNMF and Semi-NMF: [](https://colab.research.google.com/drive/1psE4HOAwdJ74fle_KfNtoXOAPWG533yp?usp=drive_link)