LeJEPA achieves linear identifiability of latent variables uniquely when the latents are Gaussian in worlds with stationary additive-noise transitions.
super hub Mixed citations
Understanding intermediate layers using linear classifier probes
Mixed citation behavior. Most common role is method (53%).
123
Pith papers citing it
Method
53% of classified citations
abstract
Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes", trained entirely independently of the model itself. This helps us better understand the roles and dynamics of the intermediate layers. We demonstrate how this can be used to develop a better intuition about models and to diagnose potential problems. We apply this technique to the popular models Inception v3 and Resnet-50. Among other things, we observe experimentally that the linear separability of features increase monotonically along the depth of the model.
hub tools
citation-role summary
method 10
background 9
citation-polarity summary
claims ledger
- abstract Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes", trained entirely independently of the model itself. This helps us better understand the roles and dynamics of the intermediate layers. We demonstrate how this can be used to develop a better intuition about models and to diagnose potential problems. We apply this technique to the popular models Inception v3 and Resnet-50. Among other things, we observe exper
authors
co-cited works
representative citing papers
A Particle Transformer jet tagger contains a sparse six-head circuit whose source-relay-readout structure recovers most performance and whose residual stream preferentially encodes 2-prong energy correlators.
AVLLMs encode audio semantics in middle layers but suppress them in final text outputs when audio conflicts with vision, due to training that largely inherits from vision-language base models.
Transformers performing in-context learning implicitly implement gradient descent, ridge regression, and least-squares predictors for linear models, with behavior shifting based on model depth, width, and data noise.
LLM activations encode current and prior entities in orthogonal slots, but models only use the current slot for explicit factual retrieval despite prior-slot information being linearly decodable.
LBR performs token-level test-time scaling via local branch routing on hidden states, enabling end-to-end RL training and improving Pass@1 and Pass@32 on math benchmarks over CoT and RLVR baselines.
VLMs across families and scales show anchoring to discrete slant angles in zero-shot and prompted settings rather than human-like graded texture-based slant perception.
SASA replaces single-vector decoders in SAEs with learned subspaces plus block sparsity and nuclear-norm regularization, proving that a single group becomes the global minimizer once block size meets intrinsic dimension and yielding polynomial rather than exponential sample complexity.
Introduces SARL benchmark showing pretrained audio encoders encode source-level spatial factors more readily than room-level factors, with patterns shaped by input configuration and training paradigm.
Face-Feature Tuning is a label-free logit remapping method that reduces FPR/TPR gaps across groups in deepfake detection while preserving overall accuracy.
UWM-JEPA uses a density-matrix latent and unitary predictor in JEPA to preserve joint-state spectrum during blind rollouts, achieving 0.77 accuracy on a five-step hidden-velocity task versus 0.53 for an LSTM baseline.
Introduces the Perception-Physics Paradox and TC-Bench benchmark demonstrating that vision foundation models rely on visual shortcuts that fail in intense regimes rather than achieving scientific alignment via structural isomorphism.
LASH adaptively composes multiple jailbreak seed prompts via genetic search over subsets and mixture weights to reach 84.5% keyword ASR and 74.5% two-stage ASR on JailbreakBench while using only 30 queries per prompt.
This paper presents Markovian Circuit Tracing (MCT) as a benchmark and pipeline to extract and test state-transition structures in transformer activations using synthetic HMM tasks, demonstrating that state patching improves counterfactual predictions.
MAPS provides 2618 validated 3D meshes and a controllable rendering pipeline to attribute vision model recognition failures to specific scene parameters, finding camera distance and elevation as the dominant failure factors across 20 tested models.
LLM societies in Nomic show non-monotonic collective adaptation peaking at mid-scales, with smaller models rule-inert and larger ones restrictive.
Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.
Projecting LLM hidden states onto F2 algebra with 42 pairs yields 93% zero-shot accuracy on logical relations and identifies prompt-preventable late-layer collapse.
A formal construction and synthetic experiment demonstrate that proxy rankings of pretraining datasets can reverse OOD accuracy rankings.
Symmetry under affine reparameterizations of hidden coordinates selects a unique hierarchy of shallow coordinate-stable probes and a probe-visible quotient for cross-model transfer.
The paper introduces compositional interpretability as a category-theoretic framework that casts mechanistic explanations as commuting syntactic-semantic mappings optimized under faithfulness and complexity constraints derived from minimum description length.
A new orthogonal projection module for video anomaly detection suppresses facial attributes via weak face-presence signals and cosine alignment while preserving anomaly-relevant features like pose and motion.
SeBA is a joint-embedding framework that separates tabular data into two complementary views and aligns one view's representations to the nearest-neighbor structure of the other, improving feature-label relationships and achieving SOTA results in most benchmarks without relying on augmentations.
LOVER creates an unsupervised logic-regularized verifier that reaches 95% of supervised verifier performance on reasoning tasks across 10 datasets.
citing papers explorer
-
Do Audio-Visual Large Language Models Really See and Hear?
AVLLMs encode audio semantics in middle layers but suppress them in final text outputs when audio conflicts with vision, due to training that largely inherits from vision-language base models.
-
Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces
Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.
-
Inference Time Causal Probing in LLMs
HDMI is a new probe-free technique that steers LLM hidden states via margin objectives to achieve more reliable causal interventions than prior probe-based methods on standard benchmarks.
-
Graph-Native Reinforcement Learning Enables Traceable Scientific Hypothesis Generation through Conceptual Recombination
Graph-PRefLexOR fine-tunes graph-native models with GRPO to organize reasoning into phases, yielding 40-65% gains in traceable hypothesis generation and 2-3x semantic diversity on 100 materials science questions.
-
AEGIS: A Backup Reflex for Physical AI
AEGIS uses activation probes for early-warning detection of high-risk steps in weak policies and selectively escalates to stronger policies, recovering 10.1% of lost trajectories on LIBERO-Spatial while activating the strong policy on only 38% of steps.
-
An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
LRMs show a large production-evaluation gap on the VAIR dataset with valid answers but invalid reasoning, driven by answer confirmation bias as evidenced by CoT analysis, linear probes, and causal patching.
-
$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing
D²-Monitor routes between lightweight and heavy safety probes using the count of hesitation steps in diffusion LLM denoising trajectories, achieving SOTA trade-off on three datasets with under 0.85M parameters.
-
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
Attention to goal tokens declines in multi-turn LLM interactions while residual representations often retain decodable goal information, and the gap between these predicts whether goal-conditioned behavior survives.
-
When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel
CoT traces align with internal answer commitment in only 61.9% of steps on average, dominated by confabulated continuations after commitment has stabilized.
-
The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations
Temporal knowledge drift is encoded as a geometrically orthogonal direction in LLM residual streams, independent of correctness and uncertainty.
-
Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
Omni-modal LLMs exhibit visual preference that emerges in mid-to-late layers, enabling hallucination detection without task-specific training.
-
Primary ICD Category Prediction using LLM-based Probing
Linear probing of frozen medical LLM representations unifies structured and unstructured EHR data for primary ICD category prediction, outperforming single-modality probes and baselines while enabling cross-dataset adaptation via a small adapter.
-
Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking
SBBT separates Brier-score calibration gains from AUROC ranking gains in prefix-conditioned success estimation for LLM math reasoning, with structure-aware signals yielding up to +0.110 AUROC over baselines.
-
HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory
HyperLens reveals that deeper transformer layers magnify small confidence changes into fine-grained trajectories, allowing quantification of cognitive effort where complex tasks demand more and standard SFT can reduce it.
-
Decodable but Not Corrected by Fixed Residual-Stream Linear Steering: Evidence from Medical LLM Failure Regimes
Overthinking in medical QA is linearly decodable at 71.6% accuracy yet fixed residual-stream steering yields no correction across 29 configurations, while enabling selective abstention with AUROC 0.610.
-
A Model of Understanding in Deep Learning Systems
Deep learning systems achieve systematic understanding through internal models tracking regularities but exhibit fractured understanding due to symbolic misalignment, lack of explicit reduction, and weak unification.
-
Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations
Perceptual geometry for color, pitch, emotion and taste emerges transiently in intermediate layers of transformer LLMs despite purely textual training.
-
Beyond the Black Box: Interpretability of Agentic AI Tool Use
Introduces a mechanistic interpretability toolkit with SAEs and linear probes to monitor tool-use decisions and risk in AI agents from internal activations before execution.