arXiv subjects

Anton Korznikov

Publications and source records attributed to Anton Korznikov.

8 recordsLinked to original sources

arXiv2026

Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?

Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Recent work has introduced multiple SAE variants and successfully scaled them to frontier models. Despite much excitement, a growing number of negative results in downstream tasks casts doubt on whether SAEs recover meaningful features. To directly investigate this, we perform two complementary evaluations. On a synthetic setup with known ground-truth features, we demonstrate that SAEs recover only $9\%$ of true features despite achieving $71\%$ explained variance, showing that they fail at their core task even when reconstruction is strong. To evaluate SAEs on real activations, we introduce three baselines that constrain SAE feature directions or their activation patterns to random values. Through extensive experiments across multiple SAE architectures, we show that our baselines match fully-trained SAEs in interpretability (0.87 vs 0.90), sparse probing (0.69 vs 0.72), and causal editing (0.73 vs 0.72). Together, these results suggest that SAEs in their current state do not reliably decompose models' internal mechanisms.

cs.LG↗

arXiv2026

Context or Knowledge: How LLMs Attribute Their Own Answers

Language models can answer a question from a supplied document or from their parametric knowledge. When later asked where the answer came from, what determines their source report? We study this by intervening on the model's key-value (KV) cache after the answer is generated and before the source question is asked. On a controlled factual task with four models (7B-32B), changing or removing the document's cache never changes the report. In contrast, transplanting the question-and-answer (Q+A) cache between runs with identical question and answer tokens transfers it: every eligible report follows the donor, while the recipient's document is unchanged. On the two smaller models, steering Q+A values along directions fitted before any source question reverses 98.9-100% of reports across four document conditions at a fixed strength, while norm-matched random directions flip at most 1.1%. The components of keys and values along fitted directions carry the transplant effect: copying them alone nearly reproduces the report change; holding them fixed nearly prevents it. Applied during answer generation, the same value directions also change which source supplies the answer, though more weakly and depending on the prompt. Source reporting in this setting thus depends causally on cached state produced while answering. We do not establish general reporting accuracy or a complete interpretation of this state.

cs.CL↗

arXiv2026

From Stories to Features: Scaling Concept Vectors for AI Alignment & Interpretability

We study feature vectors: directions in a language model's activation space that correspond to human-interpretable concepts, such as honesty or deception. Existing unsupervised methods like sparse autoencoders attempt to recover the whole feature space, often at the cost of feature quality and interpretability. We take a more pragmatic route: focusing on concepts relevant to AI safety and alignment, we generate synthetic concept-antagonist story pairs and use the difference of their mean model activations as a feature vector. We scale this approach to 1,036 alignment-relevant concepts using 2M synthetic stories across multiple languages and genres, which we publicly release. Across six models from three model families, our feature vectors reliably generalize to detecting their corresponding concepts in chat dialogues and web text. They form an interpretable geometry shared across models and can causally steer model behavior when injected into activations. We further use these features to analyze model representations during jailbreak attacks, mathematical and agentic reasoning. Our targeted feature construction thus offers a scalable route to studying concepts in language models, potentially extending to millions of features across arbitrary domains.

cs.CL↗

arXiv2026

Sparse Transformer: a Controlled Testbed for Mechanistic Interpretability

Mechanistic interpretability aims to decompose neural network computations into human-understandable features, yet progress is limited by the absence of ground-truth units to evaluate against. We address this with a Sparse Transformer (ST): a 5-layer language model trained on TinyStories whose wide, TopK-sparse MLP forces neuron specialization. We show that ST neurons are highly interpretable: they outperform a loss-matched dense transformer by 43% on AutoInterp, and circuits of a median of 12 neurons suffice to reproduce individual model predictions. This testbed allows us to directly compare feature learning methods: Transcoder, which approximates the MLP input-output mapping, recovers ST's neuron vectors with 52.6% higher cosine similarity than Sparse Autoencoder, which only reconstructs outputs. Furthermore, the ST enables a controlled study of polysemanticity: distilling its sparse MLP into a dense counterpart reveals how compression leads to feature superposition. These results show how a known reference basis sharpens evaluation and understanding, a role we hope the ST can serve for the field.

cs.AI↗

arXiv2026

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the \textit{Superposition Linearity Hypothesis}. We provide evidence that superposition is an intrinsic property of the Transformer architecture rather than an emergent consequence of training; in fact, we observe that it tends to diminish as pretraining progresses. However, we demonstrate that linearity can be substantially restored through lightweight fine-tuning, significantly reducing the divergence between the predicted next-token distribution and the average of the individual next-token distributions. Finally, we introduce a guided decoding procedure that disentangles superposed outputs, enabling the simultaneous generation of two coherent continuations from a single forward pass.

cs.CL↗

arXiv2026

What Attention Recalls and Recurrence Controls in Hybrid Language Models

Hybrid language models combine attention with a fixed-size recurrent state, but the role of each channel remains unclear. We introduce two cache-level interventions. Split-prefill keeps only the KV cache or only the recurrent state from a prefilled context, then generates an answer. State-swap pairs the KV cache from one context with the recurrent state from another in a single forward pass. On Qwen3.5 and Falcon-H1, the two channels split sharply by function. Exact retrieval survives only through attention (64-98% of full accuracy) and collapses to zero through recurrence. Output language and persona reverse the pattern: both survive recurrence (70-80% and 3-5x) while KV-only drops to ~1% language accuracy. State-swap confirms this causally: the answer takes its value from the KV side and its language from the recurrent side. Recurrent-only generation also accepts words that were never in the context but share meaning or parts with seen items. Attention provides a lookup over what was said; the recurrent state shapes how the model says it next.

cs.CL↗

arXiv2026

The Rogue Scalpel: Activation Steering Compromises LLM Safety

Activation steering is a promising technique for controlling LLM behavior by adding semantically meaningful vectors directly into a model's hidden states during inference. It is often framed as a precise, interpretable, and potentially safer alternative to fine-tuning. We demonstrate the opposite: steering systematically breaks model alignment safeguards, making it comply with harmful requests. Through extensive experiments on different model families, we show that even steering in a random direction can increase the probability of harmful compliance from 0% to 1-13%. Alarmingly, steering benign features from a sparse autoencoder (SAE), a common source of interpretable directions, demonstrates a comparable harmful potential. Finally, we show that combining 20 randomly sampled vectors that jailbreak a single prompt creates a universal attack, significantly increasing harmful compliance on unseen requests. These results challenge the paradigm of safety through interpretability, showing that precise control over model internals does not guarantee precise control over model behavior.

cs.LG↗

arXiv2025

OrtSAE: Orthogonal Sparse Autoencoders Uncover Atomic Features

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of general features creating representation holes, and feature composition, where independent features merge into composite representations. In this work, we introduce Orthogonal SAE (OrtSAE), a novel approach aimed to mitigate these issues by enforcing orthogonality between the learned features. By implementing a new training procedure that penalizes high pairwise cosine similarity between SAE features, OrtSAE promotes the development of disentangled features while scaling linearly with the SAE size, avoiding significant computational overhead. We train OrtSAE across different models and layers and compare it with other methods. We find that OrtSAE discovers 9% more distinct features, reduces feature absorption (by 65%) and composition (by 15%), improves performance on spurious correlation removal (+6%), and achieves on-par performance for other downstream tasks compared to traditional SAEs.

cs.LG↗