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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aches

-0.72

ancial

-0.72

 pars

-0.70

 enrichment

-0.65

rates

-0.64

myra

-0.63

@@

-0.62

lime

-0.61

bread

-0.61

ificantly

-0.60

POSITIVE LOGITS

ãĤ¤ãĥĪ

0.84

 IMAGES

0.73

enegger

0.71

velt

0.70

endez

0.69

ridor

0.68

wagen

0.66

dan

0.64

 Swanson

0.63

 Bernstein

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.