Sentence Localization Task

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

• Knowledge Localizationconcept0.788
  Technique for identifying where specific knowledge is stored in neural network layers via interventions
• task generalizationconcept0.784
  The ability to generalize across tasks; lacking in latent methods.
• Tactile Localizationconcept0.781
  Chinn et al. showed that tactile target experience promotes earlier mirror self-recognition in infants; noted as a future extension
• Grammar as Positional Encoding for Languagehypothesis0.749
  Hypothesis that in language tasks, the abstract structure encoded in positional encodings corresponds to grammatical structure.
• Hinting Taskmethod0.741
  One of four ToM tasks analyzed; requires inferring speaker intent from indirect hints; scored 0/1.
• Task Difficultyconcept0.741
  The paper identifies task difficulty as a key moderator: easy MMLU questions show performative CoT, hard GPQA-Diamond questions show genuine reasoning
• Sentence localization accuracy reaches 88% at layer 2, α=5 vs. 10% chance in 10-way classificationfinding0.740
  Highest localization accuracy achieved, showing strong partial introspection for early-layer injections
• what is the analogue of spatial positional encodings for higher order tasks such as language?question0.722
  Open question raised in Discussion about extending TEM-t principles beyond spatial navigation.