Sparse autoencoders are a useful interpretability tool but are often used wastefully when a simpler, more obvious method would work as well or better

Added to korrents 19 Aug 2025 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• The saving pruning offers is only ever at inference, because the sparse architectures it produces are hard to train from the start. JFJonathan Frankle9 Mar 2018similar wordingChief AI scientist at Databricks
• As models get better at following instructions, techniques like finetuning and constrained sampling for structured outputs will become less necessary CHChip Huyen16 Jan 2024similar wordingEngineer and writer on machine-learning systems
• Complete reverse-engineering of neural networks is a less promising research direction than studying model biology and applying interpretability usefully NNNeel Nanda19 Aug 2025similar wordingRuns the mechanistic interpretability team at Google DeepMind
• The most underused thing AI does is teach you: people reach for it to write their code and forget it can take them through a curriculum in an hour. JZJulie Zhuo21 Sept 2025similar wordingCo-founder of Sundial; former vice president of product…
• Locality is what makes a language good for AI: if a single file states what it imports and what it offers, a model never has to hold the whole program at once. AHAnders Hejlsberg13 May 2026similar wordingDanish software engineer and Microsoft technical fellow

On the map

Open the map on its own page →