arXiv AI
Jul 7
Unsupervised Features Mining via Activation Geometry
arXiv:2607. 04222v1 Announce Type: new Abstract: Interpretability methods aim to reveal the features represented inside large language models (LLMs).
Measuring Semantic Abstractness of SAE Features via Nonlocality
arXiv:2608. 10537v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have helped uncover mechanistic explanations for LLM behaviours such as reasoning, jailbreaking etc.
Related stories
arXiv AI
Jul 28
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
arXiv:2607. 24645v1 Announce Type: cross Abstract: The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior.
arXiv Machine Learning
Sep 21
Exemplar Partitioning for Mechanistic Interpretability
The paper introduces Exemplar Partitioning (EP), an unsupervised technique that constructs interpretable feature dictionaries from large language model activations by clustering streamed activations into Voronoi regions defined by exemplars and their averages. EP allows comparison of dictionaries across layers, checkpoints, and architectures, and demonstrates utility in interpreting model behavior, tracking training dynamics, detecting hidden concepts, and enabling targeted interventions. Experiments on Gemma‑2‑2B and Llama‑3.1‑8B show EP can reveal how instruction tuning reorganizes harmful prompt activations, facilitate interventions that alter model responses, and achieve high concept‑detection performance while requiring far fewer construction tokens than comparable methods.
arXiv Machine Learning
Aug 11
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
arXiv:2608. 09209v1 Announce Type: cross Abstract: Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs.
arXiv AI
Jun 24
SURGELLM: Rethinking Multi-Task Evaluation through Task-Aware Feature Gating with Class-Balanced Normalization
arXiv:2606. 24259v1 Announce Type: cross Abstract: Fine-tuned encoders deployed across heterogeneous NLP tasks face three compounding problems: mismatched inductive biases, class-imbalance corruption of feature statistics, and no mechanism to condition attention on external lexical knowledge.
Hugging Face Trending Papers
Aug 10
UNMASK: Discovering and Causally Verifying Spurious Shortcuts in Text Classifiers
Neural language models trained on large crowdsourced corpora frequently exploit spurious surface patterns tied to target labels without true linguistic or causal relevance, boosting benchmark performance while failing on adversarial or out-of-distribution inputs. Existing approaches either require manual specification of the feature vocabulary or automate discovery only partially, leaving the gap between dataset-level correlation and model-level exploitation unaddressed.
Hugging Face Trending Papers
Jul 27
Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects
The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation descriptions may have weak or unexpected causal effects; steering can vary across prompts or oppose the intended direction; and activation-based feature selection can miss features that produce the desired output change.
arXiv Computation and Language
Aug 28
Reward-Informed Sparse Autoencoders and the Solution-Completeness Confound
The paper introduces Reward‑Informed Sparse Autoencoders (RI‑SAEs), which use reinforcement‑learning rewards to curate data for training sparse autoencoders on language‑model activations. On Llama‑3.1‑8B, a sparse subset of features separates high‑reward from low‑reward reasoning continuations, but control experiments show this separation largely reflects solution completeness rather than true reasoning quality. The authors conclude that reward filtering can cheaply reuse RL signals for interpretability, though most of the discovered features capture completion form rather than deep reasoning.
arXiv AI
Jun 9
Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects
arXiv:2606. 08365v1 Announce Type: cross Abstract: Sparse autoencoder (SAE) features are increasingly used to steer language models, but feature steering is rarely clean: the same intervention can behave inconsistently across contexts and perturb unrelated features.
arXiv AI
Jun 18
From Concept-Aligned Tokens to Vulnerable Features: Mechanistic Localization of Jailbreaks
arXiv:2604. 23130v2 Announce Type: replace-cross Abstract: Jailbreak attacks expose a persistent failure mode in safety-aligned LLMs: models can be pushed into harmful behavior, but the internal representations enabling this shift remain poorly localized.
arXiv Machine Learning
Jun 18
From Sparse Features to Trustworthy Proxies: Certifying SAE-Based Interpretability
arXiv:2606. 18383v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable features from language models (LMs), yet a central question remains: when can an SAE-based explanation be treated as a faithful view of an underlying frozen LM We study this through a post-hoc generalization framework that certifies the LM via a sparse proxy, obtained by replacing a native hidden activation with its pretrained SAE reconstruction.
arXiv Machine Learning
Aug 4
LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering
arXiv:2604. 03532v2 Announce Type: replace-cross Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult.