INDEX

Explanations

phrases related to geopolitical conflicts and sanctions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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

swick

-0.94

uscript

-0.74

ITNESS

-0.68

WORK

-0.68

ortun

-0.68

 Rhythm

-0.67

 Alic

-0.66

erd

-0.66

ullivan

-0.65

lihood

-0.65

POSITIVE LOGITS

 relief

1.05

 levied

1.02

 imposed

1.01

 sanctions

0.98

 regimes

0.88

 embargo

0.87

 regime

0.87

 freeze

0.81

 targeting

0.79

 prohibiting

0.78

Activations Density 10.205%

phrases related to geopolitical conflicts and sanctions

No Comments

No Known Activations