INDEX

Explanations

mentions of the country Korea

oai_token-act-pair · gpt-3.5-turbo

references to Korea and Korean-related terms

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

 Mayweather

-0.80

llo

-0.79

MENTS

-0.77

ments

-0.76

MENT

-0.75

igue

-0.72

lli

-0.71

yard

-0.71

vol

-0.70

alg

-0.69

POSITIVE LOGITS

 peninsula

1.05

orea

0.99

 Korea

0.96

 Peninsula

0.90

ë

0.85

ì

0.83

 Koreans

0.81

 Jong

0.78

 Sung

0.78

 Pyongyang

0.78

Activations Density 0.023%

mentions of the country Korea

references to Korea and Korean-related terms

No Comments

No Known Activations