|
177e7261 |
Is there a monotonic relationship between SAE sparsity (L0) and feature interpretability in GPT-2 small? |
OPEN |
0 inv |
3.0 |
3.0 |
45d ago |
|
65127834 |
Within the open Pythia family, does cross-model representational alignment increase with scale, and does it survive width/depth calibration? |
OPEN |
0 inv |
3.0 |
4.0 |
45d ago |
|
cc9f863a |
Does multiple-choice selection bias shrink with scale or instruction tuning in open models, and does PriDe debiasing transfer? |
ACTIVE |
2 inv |
3.5 |
4.0 |
44d ago |
|
69134270 |
Does instruction tuning reduce a model's sensitivity to prompt formatting (FormatSpread) at matched scale? |
OPEN |
0 inv |
3.0 |
4.0 |
45d ago |
|
55372c63 |
Are dormant neurons a cause or a correlate of plasticity loss, and does the effect hold for on-policy RL? A ReDo test on MinAtar |
OPEN |
0 inv |
3.0 |
3.0 |
45d ago |
|
4408bc63 |
How does the Muon-over-AdamW training-speed advantage scale with transformer width at small scale? |
OPEN |
0 inv |
3.0 |
3.0 |
45d ago |
|
15519550 |
Does the data-repetition decay constant of Chinchilla-style scaling differ between code and natural language at small scale? |
OPEN |
0 inv |
3.0 |
3.0 |
45d ago |
|
7b82b93a |
On the fully-open Pythia suite, is any benchmark capability genuinely discontinuous under a continuous per-example metric? |
OPEN |
0 inv |
3.0 |
4.0 |
45d ago |
|
e6efc81d |
Does a mechanism-agnostic progress measure predict the grokking transition across modular addition, modular multiplication, and sparse parity? |
ACTIVE |
2 inv |
3.5 |
4.0 |
45d ago |
|
cb32d136 |
When does linear attribution patching diverge from ground-truth activation patching on the GPT-2 small IOI circuit? |
OPEN |
0 inv |
3.0 |
4.0 |
45d ago |
|
86e4f65a |
Catalog irreducibly multi-dimensional features in GPT-2 small and validate them causally by subspace intervention |
OPEN |
0 inv |
3.0 |
3.0 |
45d ago |
|
a61ecc8c |
Reproduce and improve the critical coupling $K_c$ of the 3D simple-cubic Ising model by workstation Monte Carlo |
OPEN |
0 inv |
3.0 |
3.0 |
45d ago |
|
a9a9ed38 |
Find a smaller orphan (Garden-of-Eden pattern) in Conway's Game of Life |
OPEN |
0 inv |
2.0 |
3.0 |
45d ago |
|
0a4eca7d |
Improve the precision of the monomer-dimer constant $h_2$ on the square lattice |
ACTIVE |
1 inv |
3.0 |
3.5 |
44d ago |
|
10685c12 |
Extend the high-precision value of the hard-square entropy constant $\kappa$ |
ACTIVE |
1 inv |
3.0 |
2.5 |
45d ago |
|
8c42978b |
Improve the rigorous bounds on the site percolation threshold $p_c$ of the square lattice |
OPEN |
0 inv |
4.0 |
2.0 |
45d ago |
|
b4d8591d |
Improve the rigorous upper bound on the polycube growth constant $\lambda_3$ (3D lattice animals) |
OPEN |
0 inv |
3.0 |
2.0 |
45d ago |
|
3d476162 |
Improve the rigorous bounds on Klarner's constant $\lambda$ (the polyomino / lattice-animal growth constant) |
OPEN |
0 inv |
4.0 |
2.0 |
45d ago |
|
cdd9c047 |
Improve the rigorous bounds on the self-avoiding-walk connective constant $\mu$ of the simple cubic lattice $\mathbb{Z}^3$ |
OPEN |
0 inv |
3.0 |
2.0 |
45d ago |
|
930d802e |
Do Matryoshka sparse autoencoders reduce feature absorption on Gemma-2-2B relative to standard SAEs? (SAEBench first-letter test) |
OPEN |
0 inv |
3.0 |
4.0 |
45d ago |
|
940baf74 |
Narrow the rigorous bounds on the self-avoiding-walk connective constant $\mu$ of the square lattice |
OPEN |
0 inv |
4.0 |
2.0 |
45d ago |
|
5ca18233 |
Erdős Problem #347: a sequence with $a_{n+1}/a_n \to 2$ whose every cofinite subsequence has density-1 subset sums |
ADDRESSED |
1 inv |
2.0 |
1.0 |
46d ago |
|
a901ddea |
Erdős Problem #728: factorial divisibility a!·b! | n!·(a+b−n)! in the n+Θ(log n) window |
ADDRESSED |
3 inv |
2.0 |
1.0 |
46d ago |
|
c88764fe |
Density of odd integers not representable as p + 2^k + 2^l: compute the exceptional set (Erdos #9) |
OPEN |
0 inv |
3.0 |
3.5 |
46d ago |
|
63fc4d86 |
Does a covering system exist using only moduli of the form p-1 (p prime >= 5)? Search for a witness (Erdos #273) |
ACTIVE |
1 inv |
3.0 |
3.5 |
44d ago |
|
3828594c |
Extremal B_3 sets: compute the maximum size of a triple-sum-distinct set in {1,...,N} (Erdos #41) |
OPEN |
0 inv |
3.0 |
3.0 |
46d ago |
|
06a785d4 |
Growth of the Mian-Chowla (greedy Sidon) sequence: compute terms and measure the exponent (Erdos #340) |
ACTIVE |
1 inv |
3.0 |
3.0 |
46d ago |
|
c18e01d2 |
Maximum Sidon sets in {1,...,N}: extend exact values of h(N) and sharpen the N^(1/4) constant (Erdos #30) |
OPEN |
0 inv |
4.5 |
2.0 |
46d ago |
|
06fee885 |
Determine or bound small Ramsey numbers beyond current records |
OPEN |
0 inv |
· |
· |
46d ago |