We have 3 of 34 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
It is found and estimated that different words carry different amounts of information, and less-informative words tend to absorb more contextual information, and finer-grained selectivity enables more precise routing to promote information transmission between matched words.
This work shows that a single shared SAE can replace a collection of dedicated per-model SAEs, and combines a shared dictionary with model-specific encoder-decoder pairs to achieve near-dedicated-SAE reconstruction quality.
The results empirically show that relation geometry is not equally well-represented for all relations in semantic space, suggesting that there is a difference in how well semantic relations might be learned from distributional information alone.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
