Will Anthropic open-source the training code of their SAE interpretability effort?
Plus
4
Ṁ4652028
14%
this year, fully
31%
this year, significantly incomplete
19%
next year
22%
not before 2028
14%
We mean the code used for producing Scaling Interpretability blog post.
This question is managed and resolved by Manifold.
Get
1,000and
3.00
1,0003.00Related questions
Related questions
Will OpenAI go back on its voluntary commitment to AISI to share major new models w/AISI prior to release?
38% chance
Will xAI join the voluntary commitment by OpenAI/Anthropic to AISI to share major new models w/AISI prior to release?
59% chance
Will Google join the voluntary commitment by OpenAI/Anthropic to AISI to share major new models w/AISI prior to release?
83% chance
Will OpenAI announce that they are cooperating with Deepmind, Anthropic, Meta or Google in order to mitigate race dynamics by 2027?
64% chance
Will Anthropic Release a Reasoning model (a la o1) before OpenAI releases o3 for general users.
34% chance
Will Meta join the voluntary commitment by OpenAI/Anthropic to AISI to share major new models w/AISI prior to release?
38% chance
Will Anthropic have AI-related IP stolen before 2026?
45% chance
Will a model costing >$30M be intentionally trained to be more mechanistically interpretable by end of 2027? (see desc)
57% chance
Will Anthropic announce one of their AI systems is ASL-3 before the end of 2025?
65% chance
Will Anthropic release a “Strawberry” (OpenAI 01) equivalent model by March 12, 2025?
75% chance