INDEX

Explanations

keywords related to specific chemicals or substances, such as "marijuana" and "benzene"

oai_token-act-pair · gpt-3.5-turbo

words associated with substances and materials

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

 Folk

-0.70

 Planning

-0.69

 Finance

-0.68

Eld

-0.65

CM

-0.63

 Mental

-0.63

BI

-0.62

 Dare

-0.62

 Academic

-0.62

 Thom

-0.61

POSITIVE LOGITS

asus

0.86

 Detected

0.81

aminer

0.76

 retri

0.75

 smuggled

0.73

ocaust

0.73

 fumes

0.73

pointer

0.71

positive

0.71

washed

0.70

Activations Density 0.795%

keywords related to specific chemicals or substances, such as "marijuana" and "benzene"

words associated with substances and materials

No Comments

No Known Activations