arXiv:2606. 12629v3 Announce Type: replace-cross Abstract: The standard basis of transformer hidden states is a training-free, architecture-general feature basis for detecting concepts and, in language models, steering them; with no learned dictionary.
arXiv:2606. 12629v1 Announce Type: cross Abstract: We show that the standard basis of transformer hidden states already provides a training-free, architecture-general feature basis.
SignSeek is a new method for learning transferable sign representations that enables efficient retrieval of signs from dictionaries using only a query video. It employs contrastive learning with saliency‑guided articulator masking, aligning same‑gloss signs across signers while focusing on the single most critical articulator per sign. Trained on 266K samples from multiple sign languages, SignSeek achieves state‑of‑the‑art cross‑corpus retrieval performance and zero‑shot generalisation to unseen British Sign Language, also improving isolated sign recognition and subtitle alignment.
arXiv:2606. 31963v1 Announce Type: new Abstract: Modern LLM workflows move coordinate-indexed objects across checkpoints: steering vectors, sparse autoencoders, top-$k$ neuron sets, attribution lists, and merge alignments.
arXiv:2607. 16741v1 Announce Type: new Abstract: B\"urger et al.
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:2608. 10251v1 Announce Type: cross Abstract: A transformer's answer lives on one axis: the direction its unembedding reads.
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.
The paper introduces Contrastive Projection, a method that reads a transformer’s internal states by differencing the hidden states of two closely matched prompts and projecting the difference through the unembedding layer. This approach cancels shared components and highlights the distinctions between prompts, effectively revealing steering vectors and domain-to-domain mappings such as metaphor. The technique is training‑free, operates at every position, sub‑layer, and head, and has been validated across multiple architectures and initialization seeds.
arXiv:2609.07965v1 Announce Type: cross Abstract: Sign Language Translation has advanced with deep learning, yet evaluations remain largely signer-dependent, with overlapping signers across train/dev...
arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.
M3T introduces a discrete multi‑modal motion token system for sign language production, addressing the need for non‑manual features such as mouthings, eyebrow raises, gaze, and head movements. The approach couples FLAME’s expressive facial space with SMPL‑X body parameters and uses modality‑specific Finite Scalar Quantization VAEs to achieve high face codebook utilization (99.0%). Trained with an autoregressive transformer and a sign‑to‑text translation objective, M3T outperforms existing methods on three standard datasets, notably improving accuracy on NMFs‑CSL from 49.0% to 58.3% without large‑scale pre‑training.
The paper investigates how many transformer components influence a token prediction by measuring the absolute contribution of each unit and channel to the logit. It finds that thousands of components contribute to a single prediction, yet a small subset—often just dozens—carries the majority of the predictive mass. Across models ranging from 124 M to 7 B parameters, the proportion of the model involved in a prediction remains around one to three percent, independent of size, and the study demonstrates that specific components can be directly read and written to modify model behavior without additional training.