INDEX

Explanations

words related to the surname "ice"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

hovah

-0.80

 scrut

-0.78

 challeng

-0.72

ajo

-0.70

lisher

-0.69

omination

-0.69

¥ŀ

-0.68

yrinth

-0.66

asca

-0.66

ged

-0.65

POSITIVE LOGITS

lli

1.23

llular

1.13

lla

1.06

llo

1.01

ptive

0.91

xp

0.91

llan

0.91

ice

0.89

ll

0.86

ptives

0.83

Activations Density 0.021%

words related to the surname "ice"

No Comments

No Known Activations