INDEX

Explanations

personal identity and relationships

oai_token-act-pair · gpt-3.5-turbo

phrases that discuss identity and self-perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ingen

-0.75

İĭ

-0.73

cedented

-0.72

eties

-0.72

ŃĶ

-0.67

eworthy

-0.66

ĵ

-0.65

icy

-0.64

vity

-0.62

 Sciences

-0.61

POSITIVE LOGITS

 kidding

0.90

 belonged

0.81

 idol

0.78

 rooting

0.76

 belong

0.73

afort

0.72

 voted

0.71

abouts

0.70

 worshipped

0.70

 belongs

0.70

Activations Density 0.077%

personal identity and relationships

phrases that discuss identity and self-perception

No Comments

No Known Activations