{"total":31,"rows":[{"id":"2406.17759","title":"Interpreting Attention Layer Outputs with Sparse Autoencoders","created":"2024-06-25","cited_by_count":43,"area":"mechinterp"},{"id":"2505.10465","title":"Superposition Yields Robust Neural Scaling","created":"2025-05-15","cited_by_count":31,"area":"mechinterp"},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17,"area":"mechinterp"},{"id":"2401.12406","title":"Enhancing In-context Learning via Linear Probe Calibration","created":"2024-01-22","cited_by_count":16,"area":"mechinterp"},{"id":"2412.04139","title":"Monet: Mixture of Monosemantic Experts for Transformers","created":"2024-12-05","cited_by_count":13,"area":"mechinterp"},{"id":"2602.03051","title":"SAES-SVD: Self-Adaptive Suppression of Accumulated and Local Errors for SVD-based LLM Compression","created":"2026-02-03","cited_by_count":12,"area":"mechinterp"},{"id":"2502.18147","title":"Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations","created":"2025-02-25","cited_by_count":10,"area":"mechinterp"},{"id":"2509.13316","title":"Do Activation Verbalization Methods Convey Privileged Information?","created":"2025-09-16","cited_by_count":10,"area":"mechinterp"},{"id":"2306.07285","title":"TransCoder: Towards Unified Transferable Code Representation Learning Inspired by Human Skills","created":"2023-05-23","cited_by_count":8,"area":"mechinterp"},{"id":"2501.19066","title":"Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2506.10235","title":"LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation","created":"2025-06-11","cited_by_count":6,"area":"mechinterp"},{"id":"2605.17231","title":"FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers","created":"2026-05-17","cited_by_count":6,"area":"mechinterp"},{"id":"2607.01033","title":"The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology","created":"2026-07-01","cited_by_count":6,"area":"mechinterp"},{"id":"2510.20479","title":"RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging","created":"2025-10-23","cited_by_count":5,"area":"mechinterp"},{"id":"2605.01167","title":"Minimizing Collateral Damage in Activation Steering","created":"2026-05-01","cited_by_count":5,"area":"mechinterp"},{"id":"2204.07023","title":"Composite Code Sparse Autoencoders for first stage retrieval","created":"2022-04-14","cited_by_count":4,"area":"mechinterp"},{"id":"2604.16042","title":"Towards Intrinsic Interpretability of Large Language Models:A Survey of Design Principles and Architectures","created":"2026-04-17","cited_by_count":4,"area":"mechinterp"},{"id":"2506.13727","title":"Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs","created":"2025-06-16","cited_by_count":3,"area":"mechinterp"},{"id":"2601.19208","title":"How Do Transformers Learn to Associate Tokens: Gradient Leading Terms Bring Mechanistic Interpretability","created":"2026-01-27","cited_by_count":3,"area":"mechinterp"},{"id":"2606.04775","title":"Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control","created":"2026-06-03","cited_by_count":3,"area":"mechinterp"},{"id":"2410.07456","title":"SAGE: Scalable Ground Truth Evaluations for Large Sparse Autoencoders","created":"2024-10-09","cited_by_count":2,"area":"mechinterp"},{"id":"2602.16740","title":"Quantifying LLM Attention-Head Stability: Implications for Circuit Universality","created":"2026-02-17","cited_by_count":2,"area":"mechinterp"},{"id":"2603.10071","title":"Dissecting Chronos: Sparse Autoencoders Reveal Causal Feature Hierarchies in Time Series Foundation Models","created":"2026-03-10","cited_by_count":2,"area":"mechinterp"},{"id":"2503.18693","title":"TARDIS: Mitigating Temporal Misalignment via Representation Steering","created":"2025-03-24","cited_by_count":1,"area":"mechinterp"},{"id":"2605.09887","title":"The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws","created":"2026-05-11","cited_by_count":1,"area":"mechinterp"},{"id":"2511.23335","title":"Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach","created":"2025-11-28","cited_by_count":0,"area":"mechinterp"},{"id":"2602.00924","title":"Supervised sparse auto-encoders for interpretable and compositional representations","created":"2026-01-31","cited_by_count":0,"area":"mechinterp"},{"id":"2606.18383","title":"When Can We Trust the Sparse Lens? A Certification Framework for SAE Faithfulness","created":"2026-06-16","cited_by_count":0,"area":"mechinterp"},{"id":"2607.00083","title":"Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust","created":"2026-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2607.19386","title":"Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance","created":"2026-07-01","cited_by_count":0,"area":"mechinterp"},{"id":"2608.24952","title":"The Dialect Tax: Dialectal Biases Persist throughout the Language Modeling Pipeline","created":"2026-08-24","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}