INDEX

Explanations

welcome messages or introductory phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that include a welcoming expression or greeting

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

river

-0.75

negie

-0.75

appropri

-0.71

ariat

-0.70

rift

-0.68

nutrition

-0.64

orius

-0.64

arist

-0.64

suggest

-0.63

onel

-0.63

POSITIVE LOGITS

giving

0.92

elcome

0.89

 Welcome

0.84

prise

0.84

Welcome

0.81

ISTER

0.78

 Guest

0.73

 Surprise

0.73

prises

0.72

ISSION

0.72

Activations Density 0.013%

welcome messages or introductory phrases

phrases that include a welcoming expression or greeting

No Comments

No Known Activations