Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jey
11 months ago
|
parent
|
context
|
favorite
| on:
A ChatGPT clone, in 3000 bytes of C, backed by GPT...
This is just a practical approximation to the actual mathematical definition of GELU, which is `GELU(x) := x * Φ(x)` where Φ(x) is the CDF of the Gaussian distribution.
fluoridation
11 months ago
[–]
Isn't that just erf()?
kgwgk
11 months ago
|
parent
[–]
They are related but the error function approaches -1 for large negative numbers. Φ(x) approaches 0 and so does x * Φ(x).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: