Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Kola Ayonrinde
J++ Lens: Jacobian Filtering Enables More Faithful Workspace Lenses
Kola Ayonrinde, Anthropic Fellows, koayon@gmail.com; Jack Lindsey, Anthropic TL;DR: The J-Lens was proposed to read verbalisable representations from language model activations. We introduce the J++ Lens: an improvement to the J-Lens that enables more faithful readouts across 9–284B models. The J++ Lens filters noisy gradients before they enter the averaged Jacobian.
The Strange Science of Interpretability: Recent Papers and a Reading List for the Philosophy of Interpretability — LessWrong
TL;DR: We recently released two papers about the Philosophy of (Mechanistic) Interpretability [here and here] and a reading list [here]. We believe that building a foundation for interpretability which leverages lessons from other disciplines (philosophy, neuroscience, social science) can help us understand AI models. We also believe this is a useful area for philosophers, neuroscientists and human-computer interaction (HCI) researchers to contribute to AI Safety.
Standard SAEs Might Be Incoherent: A Choosing Problem & A “Concise” Solution — LessWrong
This work was produced as part of the ML Alignment & Theory Scholars Program - Summer 24 Cohort. TL;DR The current approach to explaining model internals is to (1) disentangle the language model representations into feature activations using a Sparse Autoencoder (SAE) and then (2) explain the corresponding feature activations using an AutoInterp process.
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations — LessWrong
This work was produced as part of the ML Alignment & Theory Scholars Program - Summer 24 Cohort, under mentorship from Lee Sharkey and Jan Kulveit. Sparse Autoencoders (SAEs) have emerged as a useful tool for interpreting the internal representations of neural networks. However, naively optimising SAEs on the for reconstruction loss and sparsity results in a preference for SAEs which are extremely wide and sparse.
Mamba Explained
The State Space Model taking on Transformers Right now, AI is eating the world. And by AI, I mean Transformers. Practically all the big breakthroughs in AI over the last few years are due to Transformers. Mamba, however, is one of an alternative class of models called State Space Models (SSMs). Importantly, for the first time, Mamba promises similar performance (and crucially similar scaling laws) as the Transformer whilst being feasible at long sequence lengths (say 1 million tokens).
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Kola
Contact Kola, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack