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

ommel

-0.76

earchers

-0.74

semble

-0.70

lection

-0.68

akura

-0.67

velt

-0.64

pattern

-0.62

arantine

-0.60

uable

-0.60

Avg

-0.58

POSITIVE LOGITS

ãĤ¼ãĤ¦ãĤ¹

0.84

é¾įå

0.78

ModLoader

0.76

ãģł

0.75

?).

0.72

?".

0.69

?),

0.69

©¶æ¥µ

0.66

 signalling

0.65

cknowled

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.