INDEX

Explanations

Google-related terms and links within text content

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

Negative Logits

LAB

-0.92

 Vest

-0.85

 vest

-0.79

baugh

-0.79

stood

-0.79

 Singer

-0.77

 capsule

-0.73

 Bauer

-0.73

 prototyp

-0.72

 Principle

-0.72

POSITIVE LOGITS

google

1.14

bsite

0.99

weather

0.99

mail

0.96

plane

0.95

cgi

0.94

oti

0.94

blogspot

0.91

frog

0.88

ijn

0.85

Activations Density 0.092%

Google-related terms and links within text content

No Known Activations