INDEX

Explanations

mentions of being under some form of authority or regulation

oai_token-act-pair · gpt-3.5-turbo

references to being subject to conditions or regulations

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

 torches

-0.66

 Euras

-0.63

 Niet

-0.62

 Trees

-0.61

 Coch

-0.60

 Serie

-0.60

Tib

-0.59

 Sutherland

-0.59

LOT

-0.59

 Kats

-0.59

POSITIVE LOGITS

ivity

1.06

ively

1.05

ivities

0.88

itatively

0.85

ĪĴ

0.83

ive

0.83

iving

0.83

itably

0.81

Reviewer

0.81

ion

0.81

Activations Density 0.018%

mentions of being under some form of authority or regulation

references to being subject to conditions or regulations

No Comments

No Known Activations