INDEX

Explanations

legal and political terms or phrases

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

isitions

-0.85

 Flask

-0.84

 Tanz

-0.82

OPLE

-0.78

Winged

-0.78

ylum

-0.78

 confiscated

-0.77

DCS

-0.76

Dialogue

-0.75

ossier

-0.74

POSITIVE LOGITS

stall

1.25

sburg

1.22

cock

1.20

corn

1.01

tel

1.00

yip

1.00

heastern

1.00

rill

0.99

sonian

0.97

eah

0.97

Activations Density 0.564%

legal and political terms or phrases

No Comments

No Known Activations