INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

externalActionCode

-0.95

taboola

-0.74

TAIN

-0.66

ggy

-0.65

earchers

-0.65

spot

-0.62

OTAL

-0.62

piece

-0.62

iP

-0.61

hoe

-0.60

POSITIVE LOGITS

adobe

0.75

itary

0.72

igans

0.72

anders

0.71

amed

0.68

Wad

0.63

 gall

0.63

arin

0.62

acht

0.61

ester

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.