INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

akeru

-0.82

utor

-0.71

outed

-0.66

ity

-0.65

igenous

-0.64

asso

-0.63

eele

-0.63

ledged

-0.61

ouf

-0.61

eatures

-0.59

POSITIVE LOGITS

SPONSORED

0.86

ï¸

0.71

ECA

0.66

âĸĳ

0.65

perture

0.64

 largeDownload

0.59

ãĥ¼ãĥĨãĤ£

0.58

ERY

0.58

PRESS

0.57

assetsadobe

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.