descriptive claim
The speaker's team repurposed a sparse autoencoder as a tool for interpreting gradients.
Tom McGrath · Designing How AI Grows — Tom McGrath · 2 Sept 2026
In their words
The transcript segments this claim was taken from
“So this is sort of, we kind of jerry-rigged an SAE into being a gradient, like a machine for gradient understanding.”Play from 19:04Report a misattribution
95%how strongly it was put, not whether it is true
65%importance to the conversation
98%confidence the claim was read correctly