diff --git a/docs/feature_extraction.md b/docs/feature_extraction.md
index 8c1d50d7..b41c1559 100644
--- a/docs/feature_extraction.md
+++ b/docs/feature_extraction.md
@@ -4,7 +4,7 @@ All of the models in `timm` have consistent mechanisms for obtaining various typ
 
 ## Penultimate Layer Features (Pre-Classifier Features)
 
-The features from the penultimate model layer can be obtained in severay ways without requiring model surgery (although feel free to do surgery). One must first decide if they want pooled or un-pooled features.
+The features from the penultimate model layer can be obtained in several ways without requiring model surgery (although feel free to do surgery). One must first decide if they want pooled or un-pooled features.
 
 ### Unpooled
 
@@ -170,4 +170,4 @@ Feature channels: [512, 2048]
 Feature reduction: [8, 8]
 torch.Size([2, 512, 40, 40])
 torch.Size([2, 2048, 40, 40])
-```
\ No newline at end of file
+```