dataset

active

dataset:the-pile

The Pile

Training corpus used for the 67M-parameter model tested with VPD.

Neighborhood — ranked by edge-count

Papers (1)

paper

Interpreting Language Model Parameters
mentions

Findings (1)

finding

VPD scales to a 4-layer 67M-parameter model trained on The Pile.
cites
Empirical demonstration of VPD on a mid-scale transformer, establishing feasibility.