INDEX

Explanations

phrases related to legal actions or regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to legal rulings and government regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

kj

-0.82

ngth

-0.80

mania

-0.75

eki

-0.73

emonium

-0.72

ORGE

-0.70

yssey

-0.69

fetched

-0.69

DragonMagazine

-0.68

ktop

-0.68

POSITIVE LOGITS

 abortions

1.34

 abortion

1.32

 transgender

1.18

gay

1.17

 homosexuality

1.15

 gays

1.15

 contraception

1.14

 polygamy

1.12

 homosexuals

1.08

 contraceptives

1.07

Activations Density 0.557%

phrases related to legal actions or regulations

terms related to legal rulings and government regulations

No Comments

No Known Activations