SAE
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations
Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control. However, what exactly SAEs extract, and, correspondingly, the scientific conclusions we can draw from them, are not obvious. Empirically, the proof is in the pudding: SAEs learn interpretable features.
Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders
arXiv:2509.22015v2 Announce Type: replace Abstract: Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, providing a powerful lens for passive feature discovery. However, this passive nature makes it difficult to systematically evaluate or analyze concepts that users explicitly care about. We introduce Concept-SAE, a framework that augments SAEs with a structured and controllable interface for probing user-defined concepts.
Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
arXiv:2606.02061v1 Announce Type: new Abstract: Dictionary learning with sparse autoencoders (SAEs) produces overcomplete bases from neural network activations that are often interpretable and reduces polysemanticity. However, features from SAEs vary substantially across random seeds -- a problem known as instability. Archetypal SAEs (Fel et al., 2025) were proposed as a general dictionary-learning intervention for more reliable concept extraction, and report more stable dictionaries at the...
Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
Announce Type: replace Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large fraction of features are never activated and are unstable. Despite variants of SAEs that attempt to mitigate these issues, they require additional data, resampling, or training.
Perplexity Can Miss SAE Feature Damage Under Quantization
Announce Type: replace Abstract: Quantization is a standard path to deploying large language models, and quantized models are typically judged acceptable when perplexity or downstream accuracy remains close to the full-precision original. But behavioral parity need not imply feature fidelity: the sparse-autoencoder (SAE) features used to interpret a full-precision model may change after weight rounding.
From Tokens to Concepts: Leveraging SAE for SPLADE
Announce Type: replace Abstract: Learned Sparse IR models, such as SPLADE, offer an excellent efficiency-effectiveness tradeoff. However, they rely on the underlying backbone vocabulary, which might hinder performance (polysemicity and synonymy) and pose a challenge for multi-lingual and multi-modal usages. To solve this limitation, we propose to replace the backbone vocabulary with a latent space of semantic concepts learned using Sparse Auto-Encoders (SAE).
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
arXiv:2606.08496v1 Announce Type: new Abstract: Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features still remains a central challenge. Current explanation methods, however, typically operate within an open-loop paradigm, failing to leverage mechanistic feedback for further refinement. In this paper, we propose SAEExplainer, a training framework utilizes activation...
Toward Identifiable Sparse Autoencoders
Announce Type: new Abstract: Recently, sparse autoencoders (SAEs) have emerged as an attractive tool for interpreting and interacting with representations in practical neural networks. While it is common empirical folklore, we also show theoretically that SAEs are highly unstable: different training runs are likely to produce different concept dictionaries and sparse codes. We characterize the model properties that hinder the stability of real-world SAEs, and address each of these problems...
A Geometric Unification of Concept Learning with Concept Cones
arXiv:2512.07355v2 Announce Type: replace Abstract: Two traditions of interpretability have evolved side by side but seldom spoken to each other: Concept Bottleneck Models (CBMs), which prescribe what a concept should be, and Sparse Autoencoders (SAEs), which discover what concepts emerge. While CBMs use supervision to align activations with human-labeled concepts, SAEs rely on sparse coding to uncover emergent ones. We show that both paradigms instantiate the same geometric structure: each...
A Geometric View for Understanding Concept Learning and Neuron Interpretation in Sparse Autoencoders
Announce Type: new Abstract: We propose a unified mathematical framework for a geometric understanding of concept learning and neuron interpretation in sparse autoencoders (SAEs). While SAEs improve interpretability of neural networks by learning sparse feature representations, a principled definition of ''concept'' and ''learning'' remains unclear. We formalize concepts as sets of data points and cast concept learning as a set-alignment problem between human-defined and model-induced concepts.