CLIP Enrichment Circuits

We investigate late circuits on CLIP's vision side to understand how they glue abstract concepts together and build more general multimodal neurons. Sidney Hough † Stanford University Kevin Liu † Stanford University Jack Ryan † Stanford University Chelsea Voss OpenAI Not published yet. No DOI yet. We build off of the work done in Multimodal Neurons in Artificial Neural Networks, diving deeper into the features in hidden layers of the CLIP model. In the spirit of the circuits agenda, we looked at individual units and their connections to attempt to unravel a small part of the algorithm CLIP uses to identify images. For context, the CLIP model we studied (CLIP-RN50) has two parts: a ResNet vision model and a Transformer language model . We investigated the ResNet side, which has as its final layer a relu layer with 2048 channels that combines via pairwise addition the activations from a conv2d layer and the previous relu layer (the residual connection). We confirm significant similaritie

CLIP Enrichment Circuits We investigate late circuits on CLIP's vision side to understand how they glue abstract concepts together and build more general multimodal neurons. Context We build off of the work done in Multimodal Neurons in Artificial Neural Networks , diving deeper into the features in hidden layers of the CLIP model . In the spirit of the circuits agenda , we looked at individual units and their connections to attempt to unravel a small part of the algorithm CLIP uses to identify images. For context, the CLIP model we studied (CLIP-RN50 This is a smaller model than the RN50-4x v

related reading

• Zoom In: An Introduction to Circuitsdistill.pub
• Circuit Tracing: Revealing Computational Graphs in Language Modelstransformer-circuits.pub
• On the Biology of a Large Language Modeltransformer-circuits.pub
• Toy Models of Superpositiontransformer-circuits.pub
• Multimodal Neurons in Artificial Neural Networksdistill.pub
• Language Model Circuits Are Sparse in the Neuron Basis | Transluce AItransluce.org
• Transformer Circuits Threadtransformer-circuits.pub
• Feature Visualizationdistill.pub
• Distill — Latest articles about machine learningdistill.pub
• The Building Blocks of Interpretabilitydistill.pub
• Multimodal interpretability in 2024soniajoseph.ai
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org