INDEX

Explanations

comparisons between the harm and safety of alcohol and marijuana, arguments against vaccines, and statistical information regarding vaccine injury claims

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

comparisons of the safety and harmfulness of substances, particularly marijuana and alcohol

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

utenberg

-0.81

orsi

-0.77

prises

-0.77

umbnail

-0.76

zb

-0.73

isen

-0.73

isions

-0.72

clave

-0.72

enhagen

-0.71

 Horizons

-0.71

POSITIVE LOGITS

 harmful

1.32

 safer

1.31

 addictive

1.28

 safe

1.24

 healthier

1.22

 harmless

1.15

 ineffective

1.15

 carcin

1.15

 nutritious

1.13

 medically

1.13

Activations Density 0.256%

comparisons between the harm and safety of alcohol and marijuana, arguments against vaccines, and statistical information regarding vaccine injury claims

comparisons of the safety and harmfulness of substances, particularly marijuana and alcohol

No Known Activations