Symbol T

The passage around this formula

…k , so it is an unavoidably dense matrix multiply: roughly 2dn floating-point operations. The decoding step only touches the k latents that survived, so it is sparse: roughly 2dk operations. Summed and multiplied across T training tokens, a first-order compute model for training the dictionary is $C_{\mathrm{SAE}} \;\approx\; 2\,d\,(n + k)\,T$. Because published TopK configurations keep k in the tens to low hundreds while n runs into the millions, n $\gg$ k and the encoding term dominates almost entirely: $C_{\mathrm{SAE}}$ $\approx$ 2dnT . That…

Read this part in the article →