Input Injection

Architectural choice where the original input is projected and re-injected at each recurrence, studied for its effect on fixed-point convergence

Neighborhood — ranked by edge-count

paper

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.

Input-Injectivityconcept0.888
Assumption that DNN layers preserve input information by being injective; key condition for Theorem 1
Distinguishing Injected Concepts from Text Inputsfinding0.813
Models maintain ability to accurately transcribe input text while simultaneously reporting on injected thoughts, all models perform above chance, Opus 4/4.1 best.
Input-Restricted Interventionconcept0.804
Practical restriction of interventions to those producible by actual inputs; standard in DAS practice
Input-truthconcept0.778
Correctness of input statements to an LLM, as opposed to output-truth (correctness of model-generated outputs).
sensory inputconcept0.771
Input from environment that the agent models and predicts.
Concept Injectionconcept0.750
Technique of injecting activation patterns associated with specific concepts into a model's internal states to test whether self-reports reflect ground truth.
Input-Output Specificationconcept0.746
Specification relating a program's inputs and outputs, analogous to illocutionary correctness.
Residual-Stream Injectionconcept0.741
Core activation intervention: add scaled vector to residual stream at layer l during completion