INDEX

Explanations

mentions of organized crime and activities related to organization or organizing

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ault

-1.15

ths

-0.99

reys

-0.93

ixed

-0.92

ï¸ı

-0.92

shire

-0.90

geon

-0.90

onds

-0.90

vous

-0.90

some

-0.89

POSITIVE LOGITS

eering

1.58

eers

1.44

izational

1.33

 affili

1.25

urally

1.10

eer

1.09

atem

1.04

ally

0.99

ivist

0.99

ality

0.99

Activations Density 1.218%

mentions of organized crime and activities related to organization or organizing

No Comments

No Known Activations