INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hiba

-0.95

illet

-0.91

reements

-0.86

reement

-0.83

inger

-0.81

yss

-0.79

utenberg

-0.74

 certs

-0.74

ertodd

-0.72

dfx

-0.72

POSITIVE LOGITS

 Niet

0.80

 Vinyl

0.74

 Mash

0.74

pour

0.73

 Pour

0.72

Baz

0.71

 Horse

0.70

 Norse

0.69

Sop

0.69

Tud

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.