INDEX

Explanations

terms related to the LGBT community

oai_token-act-pair · gpt-4-turbo

references to the LGBTQ community and related topics

oai_token-act-pair · gpt-3.5-turbo

references to the LGBTQ+ community and issues related to discrimination

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

mington

-0.76

ither

-0.74

fulness

-0.71

lio

-0.71

lessly

-0.68

 crore

-0.66

ded

-0.65

ding

-0.63

ibble

-0.63

 Saving

-0.62

POSITIVE LOGITS

ugal

0.95

sect

0.79

ynski

0.79

Ã¨re

0.74

TY

0.74

alyst

0.74

ãĥ³ãĤ¸

0.73

0.72

TI

0.70

 Strauss

0.70

Activations Density 0.028%

terms related to the LGBT community

references to the LGBTQ community and related topics

references to the LGBTQ+ community and issues related to discrimination

No Comments

No Known Activations