Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
Paper
•
2408.00113
•
Published
•
6
delphi
community
AI & ML interests
None defined yet.
Recent Activity
delphi-suite's activity
jbrinkma
authored
a
paper
5 months ago
jbrinkma
authored
2
papers
6 months ago
jettjaniak
updated
a
model
8 months ago
jettjaniak
updated
a
dataset
8 months ago
jettjaniak
updated
a
model
8 months ago
jettjaniak
updated
5
datasets
9 months ago
delphi-suite/logprobs-stories-mamba-500k
Viewer
•
Updated
•
10.8k
•
29
delphi-suite/logprobs-stories-mamba-250k
Viewer
•
Updated
•
10.8k
•
29
delphi-suite/logprobs-stories-mamba-100k
Viewer
•
Updated
•
10.8k
•
29
delphi-suite/logprobs-stories-mamba-50k
Viewer
•
Updated
•
10.8k
•
29
delphi-suite/logprobs-stories-mamba-1m
Viewer
•
Updated
•
10.8k
•
28
transcendingvictor
updated
9
datasets
11 months ago
delphi-suite/v0-token-map
Viewer
•
Updated
•
4.1k
•
31
delphi-suite/v0-next-logprobs-llama2-25.6m
Viewer
•
Updated
•
11k
•
31
delphi-suite/v0-next-logprobs-llama2-12.8m
Viewer
•
Updated
•
11k
•
29
delphi-suite/v0-next-logprobs-llama2-6.4m
Viewer
•
Updated
•
11k
•
30
delphi-suite/v0-next-logprobs-llama2-3.2m
Viewer
•
Updated
•
11k
•
33
delphi-suite/v0-next-logprobs-llama2-1.6m
Viewer
•
Updated
•
11k
•
31
delphi-suite/v0-next-logprobs-llama2-800k
Viewer
•
Updated
•
11k
•
31
delphi-suite/v0-next-logprobs-llama2-400k
Viewer
•
Updated
•
11k
•
31
delphi-suite/v0-next-logprobs-llama2-200k
Viewer
•
Updated
•
11k
•
33