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

é¾įå¥ĳå£«

-0.68

 Elite

-0.65

 elite

-0.65

."

-0.62

blood

-0.61

rained

-0.61

 itch

-0.60

xual

-0.58

incial

-0.58

 flare

-0.58

POSITIVE LOGITS

ãĤ¨ãĥ«

0.85

saf

0.80

ambo

0.72

ashtra

0.72

fax

0.71

olia

0.70

 Fiorina

0.69

 âĵĺ

0.66

enthal

0.65

Ĥª

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.