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

anz

-1.03

eon

-0.79

anke

-0.79

hw

-0.76

wa

-0.74

zzy

-0.74

uld

-0.74

rek

-0.73

vt

-0.72

eva

-0.72

POSITIVE LOGITS

NCT

0.80

Aux

0.66

iques

0.64

 Franchise

0.64

 Thunder

0.61

 sides

0.61

 Electrical

0.60

 conc

0.60

 Friendship

0.59

 aspects

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.