INDEX

Explanations

phrases related to legal matters and regulations, specifically in the context of businesses and government compliance

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

Data Type

torch.float32

Hook Point

blocks.8.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

ĸļ

-0.83

ukong

-0.81

itability

-0.78

Ĥİ

-0.75

ONSORED

-0.74

ibal

-0.73

igmatic

-0.72

KEN

-0.71

come

-0.69

aterasu

-0.68

POSITIVE LOGITS

 accessories

0.99

 workplaces

0.97

 personalities

0.94

 institutions

0.94

 businesses

0.93

 libraries

0.93

 workshops

0.93

 occupations

0.91

 associations

0.91

 magazines

0.91

Activations Density 3.976%

phrases related to legal matters and regulations, specifically in the context of businesses and government compliance

No Comments

No Known Activations