INDEX

Explanations

mentions of contraception, contraceptives, and condoms

oai_token-act-pair · gpt-3.5-turbo

references to contraception and related reproductive health topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Reviewer

-0.96

cedented

-0.86

osta

-0.80

hov

-0.76

href

-0.74

Sent

-0.72

RAW

-0.71

«ĺ

-0.69

gs

-0.69

Lear

-0.69

POSITIVE LOGITS

 contraceptive

1.00

 condoms

1.00

 contraception

0.98

 contraceptives

0.94

 condom

0.89

ãĤ¤ãĥĪ

0.86

pill

0.76

 contrace

0.74

 screenings

0.73

sex

0.73

Activations Density 0.012%

mentions of contraception, contraceptives, and condoms

references to contraception and related reproductive health topics

No Comments

No Known Activations