INDEX

Explanations

references to a lack of something or insufficiency

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

selves

-0.75

 Circus

-0.74

Dug

-0.74

 Ribbon

-0.66

 Steps

-0.65

tnc

-0.65

ctors

-0.64

Ń·

-0.64

 Grac

-0.63

steen

-0.62

POSITIVE LOGITS

lust

1.43

luster

1.19

lessly

1.09

 thereof

0.99

ada

0.89

enz

0.85

lights

0.79

Reloaded

0.75

ivity

0.75

ion

0.75

Activations Density 7.246%

references to a lack of something or insufficiency

No Comments

No Known Activations