INDEX

Explanations

invalid email addresses

oai_token-act-pair · gpt-3.5-turbo

instances of invalid email notifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ynthesis

-0.69

renches

-0.67

bian

-0.67

ulz

-0.66

hens

-0.65

krit

-0.65

hip

-0.63

rooms

-0.63

eches

-0.62

mens

-0.62

POSITIVE LOGITS

 Invalid

0.94

AMI

0.87

ities

0.86

LAND

0.77

 Email

0.74

 Bagg

0.73

ATED

0.71

nit

0.69

itable

0.69

ROR

0.68

Activations Density 0.022%

invalid email addresses

instances of invalid email notifications

No Comments

No Known Activations