Will it be possible to disentangle most of the features learned by a model comparable to GPT-2 this decade?

Will mechanistic interpretability be essentially solved for GPT-3 before 2030?

Will mechanistic interpretability be essentially solved for GPT-4 before 2030?

Will we have an open-source model that is equivalent GPT-4 by end of 2025?

[Metaculus] Will an LLM at least on the scale of GPT-4 be widely available for download before January 1st, 2025?

Will a language model comparable to GPT-4 be trained, with ~1/10th the amount of energy it took train GPT-4, by 2028?

Will a model as great as GPT-5 be available to the public in 2025?

Will any open source LLM with <20 billion parameters outperform GPT-4 on most language benchmarks by the end of 2024?

By 2028, will there be a language model of less than 10B parameters that is superior to GPT-4?

By the end of 2026, will we have transparency into any useful internal pattern within a Large Language Model whose semantics would have been unfamiliar to AI and cognitive science in 2006?