54 citations · 128 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023★ 54 cited
Progress measures for grokking via mechanistic interpretability
Neel Nanda, Lawrence Chan, Tom Lieberum +2
Neural networks often exhibit emergent behavior, where qualitatively new capabilities arise from scaling up the amount of parameters, training data, or training steps. One approach…
cs.LG2022★ 29 cited
REAL ML: Recognizing, Exploring, and Articulating Limitations of Machine Learning Research
Jessie J. Smith, Saleema Amershi, Solon Barocas +2
Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible. D…