INDEX

Explanations

mentions of political figures and activities related to politics

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

 Sidd

-1.12

IELD

-1.02

UGE

-1.01

ADE

-0.99

ORGE

-0.99

enegger

-0.95

 Goldberg

-0.94

VEL

-0.89

HEAD

-0.87

 Learning

-0.87

POSITIVE LOGITS

itives

1.79

itive

1.72

§

1.54

ĭ

1.53

otaur

1.52

eties

1.52

Ľ

1.51

İ

1.48

acy

1.47

į

1.43

Activations Density 2.188%

mentions of political figures and activities related to politics

No Comments

No Known Activations