Introduces Causal Functional Signatures grounded in causal evidence and ILP-learned architectural signatures to enable explicit, comparable, and portable mechanistic claims across model scales.
The Twelfth International Conference on Learning Representations , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
A learned weighted sum of intermediate-layer activations compresses an instruction prompt into a single patch vector that, injected at an early layer, recovers task accuracy within ~2% of the full prompt.
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
Introduces the Manifold Probe to discover representation manifolds in superposition and demonstrates causal steering on time concepts in Llama 2-7b.
citing papers explorer
-
From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
Introduces Causal Functional Signatures grounded in causal evidence and ILP-learned architectural signatures to enable explicit, comparable, and portable mechanistic claims across model scales.
-
Prompt Compression via Activation Aggregation
A learned weighted sum of intermediate-layer activations compresses an instruction prompt into a single patch vector that, injected at an early layer, recovers task accuracy within ~2% of the full prompt.
-
Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States
COAST applies contrastive conceptors to steer VLA hidden states into task-specific success subspaces, yielding over 20% simulation and 40% real-robot success rate gains across three distinct policies.
-
The Grounding Gap: How LLMs Anchor the Meaning of Abstract Concepts Differently from Humans
LLMs show a grounding gap with humans on abstract concepts, with property-generation correlations at most r=0.37 versus human-to-human r>0.9, though larger models align better on explicit rating tasks and internal SAE features capture some grounding dimensions.
-
Minimizing Collateral Damage in Activation Steering
Activation steering is cast as constrained optimization that minimizes collateral damage by weighting perturbations according to the empirical second-moment matrix of activations instead of assuming isotropy.
-
Probing for Representation Manifolds in Superposition
Introduces the Manifold Probe to discover representation manifolds in superposition and demonstrates causal steering on time concepts in Llama 2-7b.