Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
carboniferous_umbraculum
Karma:
540
All
Posts
Comments
New
Top
Old
[Linkpost] Remarks on the Convergence in Distribution of Random Neural Networks to Gaussian Processes in the Infinite Width Limit
carboniferous_umbraculum
Nov 30, 2023, 2:01 PM
9
points
0
comments
1
min read
LW
link
(drive.google.com)
Short Remark on the (subjective) mathematical ‘naturalness’ of the Nanda—Lieberum addition modulo 113 algorithm
carboniferous_umbraculum
Jun 1, 2023, 11:31 AM
104
points
12
comments
2
min read
LW
link
A Neural Network undergoing Gradient-based Training as a Complex System
carboniferous_umbraculum
Feb 19, 2023, 10:08 PM
22
points
1
comment
19
min read
LW
link
Notes on the Mathematics of LLM Architectures
carboniferous_umbraculum
Feb 9, 2023, 1:45 AM
12
points
2
comments
1
min read
LW
link
(drive.google.com)
On Developing a Mathematical Theory of Interpretability
carboniferous_umbraculum
Feb 9, 2023, 1:45 AM
64
points
8
comments
6
min read
LW
link
Some Notes on the mathematics of Toy Autoencoding Problems
carboniferous_umbraculum
Dec 22, 2022, 5:21 PM
18
points
1
comment
12
min read
LW
link
Behaviour Manifolds and the Hessian of the Total Loss—Notes and Criticism
carboniferous_umbraculum
Sep 3, 2022, 12:15 AM
35
points
5
comments
6
min read
LW
link
A brief note on Simplicity Bias
carboniferous_umbraculum
Aug 14, 2022, 2:05 AM
20
points
0
comments
4
min read
LW
link
Notes on Learning the Prior
carboniferous_umbraculum
Jul 15, 2022, 5:28 PM
25
points
2
comments
25
min read
LW
link
An observation about Hubinger et al.’s framework for learned optimization
carboniferous_umbraculum
May 13, 2022, 4:20 PM
34
points
9
comments
8
min read
LW
link
Back to top