Update app.py

app.py

@@ -293,6 +293,34 @@ def create_interface():
         subject = gr.Dropdown(choices=['astroPH', 'csLG'], label="Select Subject", value='astroPH')
         
         with gr.Tabs():
+
+            with gr.Tab("Home"):
+                gr.Markdown("""
+                # SAErch: Sparse Autoencoder-enhanced Semantic Search
+
+                Welcome to SAErch, an innovative approach to semantic search using Sparse Autoencoders (SAEs) trained on dense text embeddings.
+
+                ## Key Concepts:
+
+                1. **Sparse Autoencoders (SAEs)**: Neural networks that learn to reconstruct input data using a sparse set of features, helping to disentangle complex representations.
+
+                2. **Feature Families**: Groups of related SAE features that represent concepts at varying levels of abstraction.
+
+                3. **Embedding Interventions**: Technique to modify search queries by manipulating specific semantic features identified by the SAE.
+
+                ## How It Works:
+
+                1. SAEs are trained on embeddings from scientific paper abstracts.
+                2. The SAE learns interpretable features that capture various semantic concepts.
+                3. Users can interact with these features to fine-tune search queries.
+                4. The system performs semantic search using the modified embeddings.
+
+                Explore the "SAErch" tab to try out the semantic search capabilities, or dive into the "Feature Visualisation" tab to examine the learned features in more detail.
+
+                This tool demonstrates how SAEs can bridge the gap between the semantic richness of dense embeddings and the interpretability of sparse representations, offering new possibilities for precise and explainable semantic search.
+                """)
+
+
             with gr.Tab("SAErch"):
                 input_text = gr.Textbox(label="input")
                 search_results_state = gr.State([])