thinker:curt-tiggesCurt Tigges
Authored papers (3)
Lifting the featurizer's atom from a direction to a block of directions recovers concept manifolds that SAEs shatter, and block sparsity is the MAP-matched prior for a representation that is a sparse Minkowski sum of low-dimensional manifolds. The paper introduces block-sparse featurizers (BSFs) in three variants: Vanilla (top-k blocks by norm, untied encoder), Grassmannian (tied encoder with orthonormal charts), and Group Lasso (block soft-threshold). On a synthetic manifold-superposition toy, all three reach per-block R² of 0.93–0.97 against an oracle of 0.99, while a TopK SAE collapses to 0.53. On DINOv3 ViT-B, a minimum-description-length analysis at the 20% distortion floor shows blocks of dimension 2–4 describe activations in fewer bits than b=1 SAEs at every dictionary width and sparsity, and stable rank saturates near 3 even when b=16 is allowed. In InceptionV1, the curve-detector neurons and SAE atoms are fragments of one curve manifold, whose first three Fourier harmonics carry 89% of variance (59/18/12%) and survive a matched null by factors of 470 and 314. A DINOv3 block tracks sun luminance and shadow across twelve Blender models, and SDXL blocks support manifold steering, as in the pretzel block. The implication is that a featurizer is a hypothesis about the data-generating process, so interpretability should infer what the atoms must be rather than assume them. Blocks are one answer, matched to vision but probably not to language.
Gains on the sparsity-fidelity frontier do not predict how well a sparse autoencoder performs on downstream tasks, and SAEBench demonstrates this by scoring over 200 SAEs on eight metrics. Matryoshka BatchTopK SAEs rank below TopK and BatchTopK on loss recovered, yet they take the best score on Absorption, RAVEL, Sparse Probing, SCR and TPP, which is 5 of 8 metrics, in the typical L0 range of 40-200. Matryoshka is also the only architecture whose disentanglement scores improve when width grows from 4k to 16k to 65k latents on Gemma-2-2B (layer 12). The other architectures show inverse scaling on absorption and SCR, and the effect persists when the number of ablated latents is held fixed. SAEBench combines four capability groups (concept detection, interpretability, reconstruction, feature disentanglement). It adds two novel zero-ablation metrics, Spurious Correlation Removal and Targeted Probe Perturbation, and it extends the absorption metric to partial and shared absorption. The suite covers seven architectures (ReLU, TopK, BatchTopK, Gated, JumpReLU, P-annealing, Matryoshka), Gemma-2-2B and Pythia-160M, and Gemma-Scope SAEs up to 1M latents. Hierarchical architectures beat the rest by 30-40% on SCR and absorption. No single L0 wins everywhere, though L0 of 50-150 is a reasonable compromise. The implication is that SAE progress needs a multi-metric benchmark, and that optimizing reconstruction at fixed sparsity can hide failures in concept isolation, which grow with scale. The paper declines to combine the metrics into one score.
At sufficient scale, LLMs linearly represent the truth or falsehood of factual statements in their internal activations — a claim supported by PCA visualizations, cross-dataset probe transfer, and causal intervention experiments conducted on the LLaMA-2-7B, 13B, and 70B family. PCA of residual stream activations at the most-downstream causally-implicated hidden state (group (b), e.g., layer 15 of LLaMA-2-13B over end-of-sentence punctuation) reveals clear linear separation of true and false statements across structurally and topically diverse datasets including cities (1,496 rows), sp_en_trans (354 rows), larger_than/smaller_than (1,980 rows each), and uncurated datasets from Azaria & Mitchell and Casper et al. The paper introduces mass-mean probing (MM), an optimization-free method that computes the difference-in-means direction between true and false activations and optionally applies a covariance correction, and shows MM outperforms logistic regression and contrast-consistent search (CCS) on causal intervention metrics in 7 of 8 experimental conditions, achieving normalized indirect effects as high as 0.97 (false→true) on sp_en_trans for LLaMA-2-13B with cities+neg_cities training data, despite comparable classification accuracy across methods. Probes trained on larger_than+smaller_than achieve >95% accuracy on sp_en_trans for LLaMA-2-13B and 70B, a cross-topic generalization that fails for LLaMA-2-7B, where representations cluster by surface-level token features instead. The paper argues this implies that truth has a geometrically coherent, causally active linear representation in large transformers, and that interventions targeting this direction can reliably flip a model's expressed truth judgments on out-of-distribution inputs.
More papers — OpenAlex / S2
Affiliations (1)
- Decode Research(institute)
Co-authors (12)
- Can Rager13 shared
- Adam Karvonen9 shared
- Arthur Conmy9 shared
- Demian Till9 shared
- Johnny Lin9 shared
- Joseph Bloom9 shared
- Kola Ayonrinde9 shared
- Matthew Wearden9 shared
- Neel Nanda9 shared
- Atticus Geiger6 shared
- Callum Stuart McDougall6 shared
- Chanin, David6 shared
Their work is cited by (10)
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks1× refs
- Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering1× refs
- When Models Manipulate Manifolds: The Geometry of a Counting Task1× refs
- From Directions to Cones: Exploring Multidimensional Representations of Propositional Facts in LLMs1× refs
- Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers1× refs
- Steering at the Source: Style Modulation Heads for Robust Persona Control1× refs
- Testing the Limits of Truth Directions in LLMs1× refs
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior1× refs
- Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations1× refs
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts1× refs
Other inbound relations (2)
Recent mentions (3)
- papers-typedkarvonen-2025-saebench-comprehensive.md
- papers-typedmarks-2023-geometry-truth.md
- papers-typedfu-chieh-2025-unveiling-latent.md