INDEX

Explanations

sexual and erotic terms and actions

oai_token-act-pair · gpt-3.5-turbo

references to sexual activities and explicit content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¾

-0.79

APD

-0.75

 FEMA

-0.74

é¾įå¥ĳå£«

-0.72

REE

-0.72

 Canaver

-0.72

£ı

-0.71

ETF

-0.70

 Brewery

-0.69

 condem

-0.68

POSITIVE LOGITS

 erotic

1.22

sex

1.11

 nude

1.10

 slut

1.10

 virginity

1.08

 kissing

1.07

 pussy

1.06

 sexy

1.06

 nipples

1.05

 boobs

1.05

Activations Density 0.349%

sexual and erotic terms and actions

references to sexual activities and explicit content

No Comments

No Known Activations