OpenWebText / OpenWebText-10k

anchor

Findings

• IC-052GPT-2 small's IOI circuit activations are linearly decomposable into features for the io, s, and pos attributes, with the l10h0 name mover's attention decomposing into sparse pairwise feature interactions [source]
• IC-1199GPT-2 next-token distributions contain correctable tail errors from the softmax bottleneck that degrade generation quality under low-entropy sampling, with basis-aware threshold sampling improving MAUVE across all four sizes [eval]
• IC-1200GPT-2-XL's untruncated next-token log-probability matrix has rank saturating at its hidden dimensionality of 1600, while truncation sampling produces post-truncation distributions whose estimated rank grows far beyond 1600 [eval]
• IC-205Gemma 2's SAE features exhibit depth-dependent organization, with polysemantic features in early layers and persistent, matchable features in later layers [eval]
• IC-796GPT-2 Small MLP weight matrices are full-rank across all 12 layers and residual stream features are linearly recoverable from post-GELU MLP hidden activations, providing the structural conditions for the subspace patching illusion [eval]
• IC-808Sparse autoencoder features in Pythia-70m's residual stream are more interpretable than PCA, ICA, random, and default-basis directions, with the advantage declining from early to late layers [eval]