Search Results for author:
Found 7 papers, 6 papers with code
Does Transformer Interpretability Transfer to RNNs?
Recent advances in recurrent neural network architectures, such as Mamba and RWKV, have enabled RNNs to match or exceed the performance of equal-size transformers in terms of language modeling perplexity and downstream evaluations, suggesting that future systems may be built on completely new architectures.
Neural Networks Learn Statistics of Increasing Complexity
The distributional simplicity bias (DSB) posits that neural networks learn low-order moments of the data distribution first, before moving on to higher-order correlations.
Eliciting Latent Knowledge from Quirky Language Models
Eliciting Latent Knowledge (ELK) aims to find patterns in a capable neural network's activations that robustly track the true state of the world, especially in hard-to-verify cases where the model's output is untrusted.
LEACE: Perfect linear concept erasure in closed form
Concept erasure aims to remove specified features from a representation.
Eliciting Latent Predictions from Transformers with the Tuned Lens
We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer.
imitation: Clean Imitation Learning Implementations
imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch.
Adversarial Policies Beat Superhuman Go AIs
The core vulnerability uncovered by our attack persists even in KataGo agents adversarially trained to defend against our attack.
