concept
active
concept:partial-introspectionpartial introspection
The authors' characterization of genuine but limited introspective capability found only in early-layer injection regimes
Neighborhood — ranked by edge-count
Communities (1)
community
- LLM Introspectionassociated_with
Concepts (2)
concept
- Introspectionrelated_toThe ability of a model to observe its own past internal states or computations; claimed to be architecturally permitted by transformers.
- metacognitive spaceanalogous_toJi-An et al.'s characterization of the limited regime in which model self-report succeeds, consistent with this paper's findings
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Pearson-Vogel et al.'s finding that models can detect prior concept injections; introspective signals exist in middle layers suppressed by post-training
- Tracking of functional/computational cognitive states, distinguished from phenomenal introspection.
- The capacity of a model to self-report on its internal emotional state when its SAE features are steered, used here as a measurement tool
- Direct introspection into phenomenal consciousness; its correlation with functional introspection is an open question.
- Key gap identified in the literature; systematic self-examination processes for machine consciousness development.
- Identified gap; methods for enabling machine consciousness development through self-examination.
- The capacity to detect and report one's own internal states, measured via the five-adjective task and paradox reflection
- The central concept: the ability of a model to access and report on its internal states, as defined by the paper's criteria.