INDEX

Explanations

references to contraceptive methods

oai_token-act-pair · gpt-3.5-turbo

terms related to contraception and reproductive health

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

Reviewer

-1.11

ĪĴ

-0.87

cedented

-0.86

Ĥ¬

-0.76

osta

-0.76

hov

-0.75

IELD

-0.75

escription

-0.74

arnaev

-0.74

Ķ

-0.74

POSITIVE LOGITS

 condoms

1.00

 condom

0.84

 contraceptive

0.80

 cartridges

0.75

 contraception

0.75

 cartridge

0.73

USE

0.73

 contraceptives

0.71

 inserts

0.68

nesday

0.67

Activations Density 0.023%

references to contraceptive methods

terms related to contraception and reproductive health

No Comments

No Known Activations