arXiv:2506. 20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure.
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...
arXiv:2602. 02726v2 Announce Type: replace Abstract: Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture.
arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.
SharedSAE demonstrates that a single sparse autoencoder can replace multiple model‑specific SAEs by using a shared dictionary with model‑specific encoder‑decoder pairs. It preserves activation magnitudes, normalizes only selection scores, and supports single‑model inference via model dropout. Trained on four 1B‑scale language models, SharedSAE retains 96.6% of the mean explained variance of dedicated SAEs, shows higher cross‑model latent correlations, and allows efficient adaptation of new models to the shared latent space.
arXiv:2512. 10092v2 Announce Type: replace Abstract: Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data.
arXiv:2608. 11197v1 Announce Type: new Abstract: Shani et al.
arXiv:2606. 11722v1 Announce Type: cross Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior.
arXiv:2606. 16193v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language tasks, yet their internal visual representations remain difficult to interpret.
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:2607. 08605v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept.
arXiv:2509. 25045v3 Announce Type: replace-cross Abstract: Despite their capabilities, Large Language Models (LLMs) remain opaque with limited understanding of their internal representations.
arXiv:2607. 20652v1 Announce Type: cross Abstract: Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams.