INDEX

Explanations

numbers and statistics in the text

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

sole

-0.73

bear

-0.71

ufact

-0.70

deen

-0.68

par

-0.68

akin

-0.67

pler

-0.66

folk

-0.66

Agent

-0.66

rium

-0.66

POSITIVE LOGITS

 consecutive

1.06

 percent

0.98

 pounds

0.86

 kilometers

0.86

uously

0.83

 acres

0.82

0.81

 pages

0.80

 kilograms

0.80

 years

0.80

Activations Density 1.367%

numbers and statistics in the text

No Comments

No Known Activations