INDEX

Explanations

information related to cooking and recipes, as well as technological instructions and discussions

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

apons

-0.94

inarily

-0.93

ovies

-0.92

 Siber

-0.92

ocity

-0.91

eneg

-0.90

itures

-0.87

idth

-0.86

æ©

-0.86

irie

-0.85

POSITIVE LOGITS

bit

1.10

umen

1.01

 prick

0.94

terness

0.87

 peek

0.83

 cryptic

0.83

 awkward

0.80

 chunk

0.80

ener

0.80

 pricey

0.80

Activations Density 4.242%

information related to cooking and recipes, as well as technological instructions and discussions

No Comments

No Known Activations