zlacker
[return to "Chess-GPT's Internal World Model"]
◧
1. triyam+r51
[view]
[source]
2024-01-07 02:01:24
>>homarp+(OP)
Is a linear probe part of observability/interpretability?
◧◩
2. canjob+M51
[view]
[source]
2024-01-07 02:04:43
>>triyam+r51
Yes, a pretty fundamental technique and one of the earliest. It lets you determine which layers contain what information among other things.
[go to top]