implementation detail · filed under model architecture
Learned softmax denominator bias
An attention implementation detail in which each head has a learned bias in the softmax denominator.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Each attention head has a learned bias in the denominator of the softmax
usedmodel architecturein gpt-oss-120b and gpt-oss-20bOpenAI
Filed alongside
Other methods under model architecture :: token mixer :: softmax attention.