INDEX

Explanations

mentions of specific names and locations, such as names of people, places, and organizations

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

ratulations

-0.83

 carbohyd

-0.77

dinand

-0.73

cffff

-0.73

rification

-0.72

uyomi

-0.72

geant

-0.71

awks

-0.71

nesota

-0.70

alties

-0.70

POSITIVE LOGITS

star

0.86

light

0.76

runner

0.73

fall

0.73

smith

0.69

more

0.68

board

0.67

isance

0.66

bringer

0.66

str

0.65

Activations Density 0.343%

mentions of specific names and locations, such as names of people, places, and organizations

No Comments

No Known Activations