arXiv:2607. 20596v1 Announce Type: new Abstract: Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested.
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: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:2609. 12591v1 Announce Type: new Abstract: Foundation models are increasingly adapted through fine-tuning, model editing, and alignment procedures while retaining previously acquired capabilities.
Linear probes can decode safety‑relevant concepts such as truthfulness from language‑model activations, but probe accuracy may reflect only decodability, not causal influence on model behavior. The authors show that probe weight geometry alone cannot identify the features the model actually uses, because geometrically aligned features need not be causally relevant. They introduce a sparse‑autoencoder (SAE) decomposition that ranks features by probe alignment and gradient sensitivity, and demonstrate that ablating shared, probe‑only, and random feature sets reveals a sharp dissociation: shared features drive model output changes far more than probe‑only or random features, confirming that causal relevance requires intervention beyond weight geometry.
arXiv:2606. 03002v1 Announce Type: cross Abstract: Quantization is a standard path to deploying large language models, and a quantized model is typically judged acceptable when its perplexity or downstream accuracy stays close to the full-precision original.
The paper investigates whether sparse autoencoder (SAE) features that recur across different language settings in Gemma 2 and Gemma 3 actually have consistent causal effects on translation performance. By reproducing Wu et al.’s discovery method and extending it to multilingual prompts, the authors find over 20 frequently activating features, yet causal validation reveals that almost all have negligible or inconsistent impacts. Only one feature—Gemma 2’s (L10, 5717) and Gemma 3’s (L20, 2456)—consistently improves COMET scores when amplified and worsens them when ablated across 23 language settings, indicating a language‑agnostic translation‑initiation direction.
arXiv:2609.07876v1 Announce Type: cross Abstract: Recent methods in language model interpretability employ techniques such as sparse autoencoders to decompose residual stream contributions into linea...
arXiv:2605. 28149v2 Announce Type: replace Abstract: Sparse Autoencoders (SAEs) extract interpretable features from Large Language Model activations, but standard variants enforce non-negative latents, so a bidirectional semantic axis (e.
arXiv:2607. 10226v1 Announce Type: new Abstract: We evaluate when sparse autoencoder (SAE) features act as localized control handles for safety-relevant behavior.
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:2604. 26866v2 Announce Type: replace-cross Abstract: Large language models (LLMs) acquire most of their factual knowledge during the pre-training stage, through next token prediction.
arXiv:2606. 14990v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are standard tools for mechanistic interpretability, but current SAE families are constrained by fixed encoder nonlinearities such as ReLU, JumpReLU, and TopK.