REVIEW 19 cited by
Improving Steering Vectors by Targeting Sparse Autoencoder Features
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier than finetuning, and may be more robust than prompting. However, it can be difficult to anticipate the effects of steering vectors produced by methods such as CAA [Panickssery et al., 2024] or the direct use of SAE latents [Templeton et al., 2024]. In our work, we address this issue by using SAEs to measure the effects of steering vectors, giving us a method that can be used to understand the causal effect of any steering vector intervention. We use this method for measuring causal effects to develop an improved steering method, SAE-Targeted Steering (SAE-TS), which finds steering vectors to target specific SAE features while minimizing unintended side effects. We show that overall, SAE-TS balances steering effects with coherence better than CAA and SAE feature steering, when evaluated on a range of tasks.
Forward citations
Cited by 19 Pith papers
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA optimizes continuous combinations of valid editing directions in latent space to produce realistic adversarial prompts that elicit hallucinations more effectively than prior methods, including on large reason...
-
Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference
SAE-based steering of target-language features improves multilingual inference accuracy on XCOPA, XNLI, and MGSM without parameter updates.
-
Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric Chemistry
Aurora, a foundation model fine-tuned for air quality, captures rough NOx–ozone coupling but lacks the chemical consistency and emission-plume fidelity of process-based models.
-
Sense Representations Are Inducible Interfaces
ACROS induces explicit sense representations in frozen decoder LMs via gated residual addition, enabling competitive zero-shot WSD, lexical steering, and cross-lingual adaptation on SmolLM2-360M while preserving base quality.
-
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
LLM tasks are supported by multiple distinct circuits rather than unique mechanisms, demonstrated via Overlap-Aware Sheaf Repulsion and the Distributive Dense Circuit Hypothesis.
-
RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
-
Where Steering Signals Come From: Activation Source Selection in Activation Steering
Activation steering works best when the signal comes from the state where the model is about to produce the target behavior, not from text that already shows it.
-
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
A single-token feature's causal necessity under zero-ablation depends on which SAE family found it: GemmaScope and BatchTopK features stay causally anchored while LlamaScope features are locally redundant.
-
Statistically Grounded Sparse-Feature Interventions for Activation-Space Control in Large Language Models
A three-statistic Borda consensus over sparse-autoencoder features produces interpretable activation steering, but usable quality-preserving shifts are rare and highly localized.
-
Perplexity Can Miss SAE Feature Damage Under Quantization
Quantization of LLMs can degrade many SAE features even when perplexity improves or stays similar, as shown by correlation measurements on frozen SAEs for Pythia-70M and Gemma-2-2B models across INT8 to INT4.
-
Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
Activation steering produces synthetic safety-violating data that improves downstream classifiers over prompting on most tested concepts when a harmonic mean of alignment, coherence, and diversity is optimized.
-
Multilingual Steering by Design: Multilingual Sparse Autoencoders and Principled Layer Selection
Multilingual SAEs strengthen cross-lingual representations for reliable steering and an intersection-based rule selects effective layers without exhaustive search.
-
REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
REALISTA generates semantically coherent adversarial prompts via latent-space optimization over input-dependent editing directions, achieving stronger hallucination elicitation than prior realistic attacks on open-sou...
-
The Cylindrical Representation Hypothesis for Language Model Steering
The Cylindrical Representation Hypothesis models concept representations in LLMs as a central axis for concept presence surrounded by a normal plane containing sensitive sectors that control activation ease, explainin...
-
The Cylindrical Representation Hypothesis for Language Model Steering
The Cylindrical Representation Hypothesis (CRH) models LLM representations as a central axis for concept activation surrounded by a normal plane containing sensitive sectors that determine steering sensitivity and int...
-
Data-Efficient Adaptation of LLMs via Attention Head Reweighting
Learning a single scalar per attention head lets LLMs adapt to few-shot text classification better than LoRA, with 200–1000x fewer trainable parameters.
-
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
SAEExplainer applies activation-guided preference optimization in two iterative rounds to improve explanations of SAE features and reduce hallucinations.
-
Steered Generation via Gradient-Based Optimization on Sparse Query Features
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
-
ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
ReGA uses safety-critical representations to guide abstraction in model-based analysis, enabling scalable detection of harmful LLM inputs with reported AUROC of 0.975 at prompt level.
Discussion (0). Sign in to comment.