diff --git a/p2/quest/neurobiber-pca.log b/p2/quest/neurobiber-pca.log
index 0bc7040..d8e1cb2 100644
--- a/p2/quest/neurobiber-pca.log
+++ b/p2/quest/neurobiber-pca.log
@@ -1,9 +1,8 @@
-starting the job at: Thu Sep  4 10:09:58 CDT 2025
+starting the job at: Thu Sep  4 10:23:23 CDT 2025
 setting up the environment
 running the neurobiber labeling script
-Number of PCs explaining 90% variance: 18
 Variance of each PCA component: [88.92832185 39.46471687 32.34601523 20.19544345 14.0083261  11.5837521
   7.82584723  6.89064989  6.07988254  5.80726367  5.49782354  4.50587747
   4.31482409  2.81997326  2.62989708  2.27205352  2.09396341  2.00076119]
 job finished, cleaning up
-job pau at: Thu Sep  4 10:10:21 CDT 2025
+job pau at: Thu Sep  4 10:23:47 CDT 2025
diff --git a/p2/quest/phase_090425_biber_kernelpca_affil.png b/p2/quest/phase_090425_biber_kernelpca_affil.png
new file mode 100644
index 0000000..872d105
Binary files /dev/null and b/p2/quest/phase_090425_biber_kernelpca_affil.png differ
diff --git a/p2/quest/python_scripts/neurobiber_PCA.py b/p2/quest/python_scripts/neurobiber_PCA.py
index 9c9b5ec..181ac74 100644
--- a/p2/quest/python_scripts/neurobiber_PCA.py
+++ b/p2/quest/python_scripts/neurobiber_PCA.py
@@ -32,7 +32,7 @@ if __name__ == "__main__":
     '''
     pca = PCA(n_components=18)
     biber_vecs_pca = pca.fit_transform(biber_vecs)
-    selected_axis = "source"    
+    selected_axis = "phase"    
     
     component_variances = np.var(biber_vecs_pca, axis=0)
     print("Variance of each PCA component:", component_variances)
@@ -41,14 +41,23 @@ if __name__ == "__main__":
     le = LabelEncoder()
     colors = le.fit_transform(biber_vec_df[selected_axis])
 
-    plt.scatter(biber_vecs_pca[:, 0], biber_vecs_pca[:, 1],
-            c=colors, edgecolor='none', alpha=0.5, cmap="viridis")
-    plt.xlabel('component 1')
-    plt.ylabel('component 2')
-    plt.colorbar()
+    plot_df = pd.DataFrame({                                              
+        "PC1": biber_vecs_pca[:, 0],                                      
+        "PC2": biber_vecs_pca[:, 1],                                      
+        selected_axis: biber_vec_df[selected_axis].astype(str),
+        "source":biber_vec_df['source'].astype(str)            
+    })     
+
+
+    g = sns.FacetGrid(plot_df, col="source", col_wrap=4, hue=selected_axis, palette="tab10", height=4, sharex=False, sharey=False)
+    g.map_dataframe(sns.scatterplot, x="PC1", y="PC2", alpha=0.7, s=40)
+    g.add_legend(title=selected_axis)
+    g.set_axis_labels("PC1", "PC2")
+    g.fig.subplots_adjust(top=0.9)
+    g.fig.suptitle(f"PCA by {selected_axis}, faceted by source")
 
     #plt.savefig("090225_biber_pca_plot.png", dpi=300) 
-    
+    '''
     plot_df = pd.DataFrame({
         "PC1": biber_vecs_pca[:, 0],
         "PC2": biber_vecs_pca[:, 1],
@@ -62,6 +71,7 @@ if __name__ == "__main__":
     plt.xlabel('component 1')
     plt.ylabel('component 2')
     plt.legend(title=selected_axis, bbox_to_anchor=(1.05, 1), loc=2)
-    plt.tight_layout()
-    plt.savefig(f"{selected_axis}_090425_biber_kernelpca_affil.png", dpi=300)
+    '''
+    g.fig.tight_layout()
+    g.savefig(f"{selected_axis}_090425_biber_kernelpca_affil.png", dpi=300)
     plt.show()
diff --git a/p2/quest/python_scripts/olmo_parallel_cat.py b/p2/quest/python_scripts/olmo_parallel_cat.py
index f20c6ce..b71ece0 100644
--- a/p2/quest/python_scripts/olmo_parallel_cat.py
+++ b/p2/quest/python_scripts/olmo_parallel_cat.py
@@ -14,7 +14,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, OlmoForCausalLM
 import csv 
 import pandas as pd 
 import re 
+
 import nltk
+nltk.download('punkt')
 # ----------------- prompts for LLM
 priming = "For the **GIVEN SENTENCE**, please categorize it into one of the defined [[CATEGORIES]]. Each [[CATEGORY]] is described in the TYPOLOGY for reference. Your task is to match the**GIVEN SENTENCE** to the **[[CATEGORY]]** that most accurately describes the content of the comment. Only provide the category as your output. Do not provide any text beyond the category name."