INDEX

Explanations

references to royalty or leadership positions, specifically focusing on queens

oai_token-act-pair · gpt-3.5-turbo

references to queens and royal figures

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

iant

-0.81

licts

-0.77

imaru

-0.77

iance

-0.72

Geo

-0.71

ugu

-0.69

 Amendment

-0.69

IGHTS

-0.67

ourke

-0.67

£ı

-0.66

POSITIVE LOGITS

 queens

1.43

 queen

1.37

bee

1.03

esses

0.93

Queen

0.93

wcs

0.81

 bees

0.81

 knight

0.80

hyde

0.78

 rook

0.76

Activations Density 0.004%

references to royalty or leadership positions, specifically focusing on queens

references to queens and royal figures

No Comments

No Known Activations