yep

.gitignore

@@ -0,0 +1 @@
+data/

app.py

@@ -55,8 +55,6 @@ def download_all_files():
 
 # Load configuration and initialize OpenAI client
 download_all_files()
-# config = yaml.safe_load(open('../config.yaml', 'r'))
-# client = OpenAI(api_key=config['jwu_openai_key'])
 
 # Load the API key from the environment variable
 api_key = os.getenv('openai_key')
@@ -100,10 +98,6 @@ def load_subject_data(subject):
     decoder = weights['decoder.weight'].cpu().numpy()
     del weights
 
-    # # Load feature families
-    # with open(families_path, 'r') as f:
-    #     feature_families = json.load(f)
-
     with open(family_analysis_path, 'r') as f:
         family_analysis = json.load(f)
 
@@ -533,11 +527,6 @@ def create_interface():
                             visualize_button = gr.Button("Visualize Feature")
                         
                         feature_info = gr.Markdown()
-                        # abstracts_heading = gr.Markdown("## Top 5 Abstracts")
-                        # top_abstracts = gr.Dataframe(
-                        #     headers=["Title", "Activation value"],
-                        #     interactive=False
-                        # )
 
                         abstracts_heading = gr.Markdown("## Top 5 Abstracts")
                         top_abstracts = gr.Dataframe(
@@ -597,46 +586,6 @@ def create_interface():
                             inputs=[feature_matches, subject],
                             outputs=[feature_info, top_abstracts, top_correlated, bottom_correlated, co_occurring_features, activation_dist, feature_search, feature_matches]
                         )
-                        # with gr.Row():
-                        #     feature_search = gr.Textbox(label="Search Feature Labels")
-                        #     feature_matches = gr.CheckboxGroup(label="Matching Features", choices=[])
-                        #     visualize_button = gr.Button("Visualize Feature")
-                        
-                        # feature_info = gr.Markdown()
-
-                        # abstracts_heading = gr.Markdown("## Top 5 Abstracts")
-                        # top_abstracts = gr.Dataframe(
-                        #     headers=["Title", "Activation value"],
-                        #     datatype=["markdown", "number"],
-                        #     interactive=False,
-                        #     wrap=True
-                        # )
-                        
-                        # gr.Markdown("## Correlated Features")
-                        # with gr.Row():
-                        #     with gr.Column(scale=1):
-                        #         gr.Markdown("### Top 5 Correlated Features")
-                        #         top_correlated = gr.Dataframe(
-                        #             headers=["Feature", "Cosine similarity"],
-                        #             interactive=False
-                        #         )
-                        #     with gr.Column(scale=1):
-                        #         gr.Markdown("### Bottom 5 Correlated Features")
-                        #         bottom_correlated = gr.Dataframe(
-                        #             headers=["Feature", "Cosine similarity"],
-                        #             interactive=False
-                        #         )
-                        
-                        # with gr.Row():
-                        #     with gr.Column(scale=1):
-                        #         gr.Markdown("## Top 5 Co-occurring Features")
-                        #         co_occurring_features = gr.Dataframe(
-                        #             headers=["Feature", "Co-occurrences"],
-                        #             interactive=False
-                        #         )
-                        #     with gr.Column(scale=1):
-                        #         gr.Markdown(f"## Activation Value Distribution")
-                        #         activation_dist = gr.Plot()
 
                     with gr.Tab("Feature Families"):
                         gr.Markdown("# Feature Families")
@@ -652,11 +601,7 @@ def create_interface():
                             datatype=["markdown", "number", "number"],
                             label="Family and Child Features"
                         )
-                        # family_dataframe = gr.Dataframe(
-                        #     headers=["Feature", "F1 Score", "Pearson Correlation"],
-                        #     datatype=["str", "number", "number"],
-                        #     label="Family and Child Features"
-                        # )
+
 
                         def search_feature_families(search_text, current_subject):
                             family_analysis = subject_data[current_subject]['family_analysis']
@@ -665,74 +610,6 @@ def create_interface():
                             matches = [family['superfeature'] for family in family_analysis if search_text.lower() in family['superfeature'].lower()]
                             return gr.CheckboxGroup(choices=matches[:10])  # Limit to top 10 matches
 
-                        # def visualize_feature_family(selected_families, current_subject):
-                        #     if not selected_families:
-                        #         return "Please select a feature family to visualize.", None
-
-                        #     selected_family = selected_families[0]  # Take the first selected family
-                        #     family_analysis = subject_data[current_subject]['family_analysis']
-                            
-                        #     family_data = next((family for family in family_analysis if family['superfeature'] == selected_family), None)
-                        #     if not family_data:
-                        #         return "Invalid feature family selected.", None
-                            
-                        #     output = f"# {family_data['superfeature']}\n\n"
-                        #     output += f"## Super Reasoning\n{family_data['super_reasoning']}\n\n"
-                            
-                        #     # Create DataFrame
-                        #     df_data = [
-                        #         {
-                        #             "Feature": family_data['superfeature'],
-                        #             "F1 Score": family_data['family_f1'],
-                        #             "Pearson Correlation": family_data['family_pearson']
-                        #         }
-                        #     ]
-                            
-                        #     for name, f1, pearson in zip(family_data['feature_names'], family_data['feature_f1'], family_data['feature_pearson']):
-                        #         df_data.append({
-                        #             "Feature": name,
-                        #             "F1 Score": f1,
-                        #             "Pearson Correlation": pearson
-                        #         })
-                            
-                        #     df = pd.DataFrame(df_data)
-                            
-                        #     return output, df
-
-                        # def visualize_feature_family(selected_families, current_subject):
-                        #     if not selected_families:
-                        #         return "Please select a feature family to visualize.", None, "", []
-
-                        #     selected_family = selected_families[0]  # Take the first selected family
-                        #     family_analysis = subject_data[current_subject]['family_analysis']
-                            
-                        #     family_data = next((family for family in family_analysis if family['superfeature'] == selected_family), None)
-                        #     if not family_data:
-                        #         return "Invalid feature family selected.", None, "", []
-                            
-                        #     output = f"# {family_data['superfeature']}\n\n"
-                        #     output += f"## Super Reasoning\n{family_data['super_reasoning']}\n\n"
-                            
-                        #     # Create DataFrame
-                        #     df_data = [
-                        #         {
-                        #             "Feature": family_data['superfeature'],
-                        #             "F1 Score": family_data['family_f1'],
-                        #             "Pearson Correlation": family_data['family_pearson']
-                        #         }
-                        #     ]
-                            
-                        #     for name, f1, pearson in zip(family_data['feature_names'], family_data['feature_f1'], family_data['feature_pearson']):
-                        #         df_data.append({
-                        #             "Feature": name,
-                        #             "F1 Score": f1,
-                        #             "Pearson Correlation": pearson
-                        #         })
-                            
-                        #     df = pd.DataFrame(df_data)
-                            
-                        #     return output, df, "", []  # Return empty string for search box and empty list for checkbox
-
                         def visualize_feature_family(selected_families, current_subject):
                             if not selected_families:
                                 return "Please select a feature family to visualize.", None, "", []
@@ -753,11 +630,6 @@ def create_interface():
                                     "F1 Score": round(family_data['family_f1'], 2),
                                     "Pearson Correlation": round(family_data['family_pearson'], 4)
                                 },
-                                # {
-                                #     "Feature": "## Child Features",
-                                #     "F1 Score": None,
-                                #     "Pearson Correlation": None
-                                # }
                             ]
                             
                             for name, f1, pearson in zip(family_data['feature_names'], family_data['feature_f1'], family_data['feature_pearson']):