INDEX

Explanations

words related to Planned Parenthood and issues surrounding its funding and controversy

oai_token-act-pair · gpt-3.5-turbo

references to Planned Parenthood

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Logged

-0.69

RW

-0.66

lass

-0.66

ez

-0.65

âĸ¬âĸ¬

-0.65

inness

-0.64

obin

-0.64

Naw

-0.64

kj

-0.62

 Commodore

-0.62

POSITIVE LOGITS

 Parenthood

1.47

 Federation

0.88

 clinics

0.86

arenthood

0.86

 affiliates

0.79

 abortion

0.74

 Clinic

0.72

 dispensaries

0.71

ervative

0.71

 pharmacies

0.70

Activations Density 0.010%

words related to Planned Parenthood and issues surrounding its funding and controversy

references to Planned Parenthood

No Comments

No Known Activations