INDEX

Explanations

statements warning about the risks of alcohol consumption

oai_token-act-pair · gpt-3.5-turbo

the presence of the abbreviation "U.S." in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ebook

-0.79

bably

-0.78

igs

-0.73

zzle

-0.71

ãĥĦ

-0.68

lets

-0.66

ests

-0.66

idious

-0.66

ients

-0.66

bler

-0.65

POSITIVE LOGITS

 Postal

1.04

 Cellular

1.00

 Geological

0.98

 Citizenship

0.96

 Embassy

0.96

 Soccer

0.96

 Customs

0.95

 Army

0.94

 Treasury

0.92

 Navy

0.92

Activations Density 0.057%

statements warning about the risks of alcohol consumption

the presence of the abbreviation "U.S." in various contexts

No Comments

No Known Activations