INDEX

Explanations

terms related to negative social attitudes and discrimination, particularly homophobia

oai_token-act-pair · gpt-3.5-turbo

references to homophobia and related themes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

coat

-0.79

thin

-0.75

 Solitaire

-0.73

Dur

-0.73

ding

-0.71

Path

-0.69

MER

-0.69

 Weaver

-0.68

hig

-0.67

vier

-0.67

POSITIVE LOGITS

 homophobic

1.24

 homophobia

0.99

 slurs

0.85

gay

0.78

yip

0.77

 barr

0.76

 sexist

0.75

gay

0.74

 prejudice

0.73

 queer

0.72

Activations Density 0.012%

terms related to negative social attitudes and discrimination, particularly homophobia

references to homophobia and related themes

No Comments

No Known Activations