Add instructions

app.py

@@ -18,6 +18,26 @@ CITATION_BUTTON_TEXT = """
 }
 """
 
+INSTRUCTIONS = """
+## Instructions to use the demo
+You can use this demo to :
+    1. Visualize the activations of the model for a given image.
+    2. Generate text with a specific feature clamped to a certain value.
+
+### Visualization of Activations
+1. Upload an image. (or use an example)
+2. Click on the "Submit" button to visualize the activations. The top-100 features will be displayed. (It might contains lots of low level features that activates on many patterns so explainable features might not rank very high)
+3. Use the slider to select a feature number.
+4. Click on the "Visualize" button to see the activation of that feature.
+
+### Steering Model
+1. Use the slider to select a feature number.
+2. Use the number input to select the feature strength.
+3. Type the text input.
+4. Upload an image. (optional)
+5. Click on the "Submit" button to generate text with the selected feature clamped to the selected strength.
+"""
+
 cached_tensor = None
 topk_indices = None
 
@@ -173,9 +193,11 @@ with gr.Blocks() as demo:
         """
         # Large Multi-modal Models Can Interpret Features in Large Multi-modal Models
 
-        🔍 [ArXiv Paper](https://arxiv.org/abs/2411.14982) | 🏠 [LMMs-Lab Homepage](https://lmms-lab.framer.ai) | 🤗 [Huggingface Collections](https://huggingface.co/collections/lmms-lab/llava-sae-674026e4e7bc8c29c70bc3a3)
+        🔍 [ArXiv Paper](https://arxiv.org/abs/2411.14982) | 🏠 [LMMs-Lab Homepage](https://lmms-lab.framer.ai) | 🤗 [Huggingface Collections](https://huggingface.co/collections/lmms-lab/llava-sae-674026e4e7bc8c29c70bc3a3) | [GitHub Repo](https://github.com/EvolvingLMMs-Lab/multimodal-sae)
         """
     )
+    with gr.Accordion("ℹ️ Instructions", open=False):
+        gr.Markdown(INSTRUCTIONS)
 
     with gr.Tabs(elem_classes="tab-buttons") as tabs:
         with gr.TabItem("Visualization of Activations", elem_id="visualization", id=0):