hypothesis
active
hypothesis:including-chat-data-in-sae-training-merges-rm-bias-features-with-generic-assistant-features

Including chat data in SAE training merges RM bias features with generic Assistant features

Explains poor features with three-dataset SAE.

Source paper

extracted_from
Building and evaluating alignment auditing agents
(2025) · Trenton Bricken · Rowan Wang · Sam Bowman

Neighborhood — ranked by edge-count

Findings (1)

finding

Concepts (1)

concept
  • Feature splitting
    associated_with
    Phenomenon where a feature in a small SAE splits into multiple finer features in a larger SAE.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.