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

ĸļ

-0.76

 Parenthood

-0.73

ãĥĦ

-0.65

 Notting

-0.63

 Bast

-0.63

 corrid

-0.62

velength

-0.60

cknow

-0.60

 louder

-0.59

¥µ

-0.59

POSITIVE LOGITS

 Meadows

0.71

PLIED

0.68

rentice

0.67

assium

0.66

brate

0.64

wick

0.64

arthy

0.64

yp

0.63

urion

0.62

endment

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.