Garcon

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2024 Mar 16 4:37
Editor
Edited
Edited
2024 Apr 15 12:48
Refs

A tool of infrastructure built to enable interpretability research at Anthropic

Running remote model via garçon and Garçon client connected to a model
 
 

Hooks

Pytorch Module Hook
exists. However, when the model scales beyond a single node, there's no obvious way to translate that workflow.
The basic interface to probes is that you can provide a “probe function”. Probe functions accept two arguments: a “save context” which can be used to save activations or data for later, and the tensor represented at this particular point in the model. Probe functions can return an updated tensor, which will replace the probed tensor in the computation, or can return None to use the original value. (this convention is borrowed from PyTorch hooks).
you need to create a probe, run the forward pass, and then separately retrieve the activations
 
rmodel.recordings() returns a dictionary indexed by probe point name.
 

Reduction on the server

 
 
 

2021

 
 

Recommendations