INDEX

Explanations

references to administrative roles and tasks

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "admin" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Reloaded

-0.76

lihood

-0.74

False

-0.73

enegger

-0.72

¶æ

-0.71

 IMAGES

-0.68

 Norn

-0.67

 Empires

-0.65

çīĪ

-0.65

Temperature

-0.65

POSITIVE LOGITS

stration

1.34

admin

1.09

 admin

1.04

isters

1.03

uthor

0.97

ister

0.97

 administ

0.93

istry

0.89

rative

0.86

 Admin

0.85

Activations Density 0.013%

references to administrative roles and tasks

occurrences of the word "admin" and its variations

No Comments

No Known Activations