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 Anthropic release a model that thinks before it responds like o1 from OpenAI by EOY 2024?
23% chance
Will Anthropic, Google, xAI or Meta release a model that thinks before it responds like o1 from OpenAI by EOY 2024?
58% chance
Do Anthropic's training updates make SAE features as interpretable?
50% chance
Will Anthropic and OpenAI collaborate substantially on a research paper before 2025?
22% chance
Will Anthropic have a major conflict involving its unique corporate structure similar to OpenAI before 2030?
51% chance
Will xAI join the voluntary commitment by OpenAI/Anthropic to AISI to share major new models w/AISI prior to release?
65% chance
Will Anthropic's April SAE Training Updates stack with Gated SAEs?
64% 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?
46% chance
Will OpenAI go back on its voluntary commitment to AISI to share major new models w/AISI prior to release?
35% chance