Andrew Stephen Fletcher
Blog
Projects
Categories
All
(1)
latent space monitoring
(1)
mechanistic interpretability
(1)
residual stream
(1)
Blog
Documenting my learning of AI Safety.
The Residual Stream
mechanistic interpretability
residual stream
latent space monitoring
This post discusses the residual stream in transformer models and builds towards using it for two examples of mechanistic interpretability: Logit Lens
(nostalgebraist 2020)
a…
Jan 28, 2026
No matching items
