added small size images

Author: golkar

_posts/2024-05-30-counting.md

@@ -5,10 +5,10 @@ authors: Siavash Golkar, Alberto Bietti, Mariel Pettee, Michael Eickenberg, Mile
 shorttitle: "Contextual Counting: A Mechanistic Study"
 date: 2024-05-30 09:23
 image: counting-splash.jpg
-smallimage: counting-splash.jpg
+smallimage: counting-s.jpg
 blurb: We introduce the Contextual Counting task, a new toy problem aimed at exploring interpretability of Transformer models in quantitative domains. We compare the performance of causal and non-causal models with different position codes and find causal models with RoPE and NoPE significantly outperform other configurations. We provide detailed explanation of how the circuits function and what makes them succeed or fail in generalization to out-of-distribution samples.
 shortblurb: We introduce the Contextual Counting task, a new toy problem aimed at exploring interpretability of Transformer models in quantitative domains.
-splashimage: /images/blog/counting/counting-splash.jpg
+splashimage: /images/blog/counting-splash.jpg
 link: 
 github_link: 
 permalink: /blog/contextual_counting/