What it does
This resource provides guidance on inspecting and manipulating the internal components of neural networks using nnsight. It applies to any PyTorch architecture.
It suits interpretability experiments on very large models, such as those with 70B+ parameters, when local GPU resources are not available. Remote execution through NDIF is optional. The resource is released under the MIT license.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 19 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 23
mechanistic-interpretability-nnsight
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.
v1.0.0As shown on www.aitmpl.com when we last read it