INDEX

Explanations

personal names

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

 traged

-0.72

 afterward

-0.72

ogether

-0.72

 outwe

-0.72

 helicop

-0.70

 afterwards

-0.70

anwhile

-0.68

 versa

-0.67

 disadvant

-0.66

—"

-0.63

POSITIVE LOGITS

reetings

0.83

 Vegan

0.81

Welcome

0.74

 Hearthstone

0.73

 Expand

0.71

 Raspberry

0.71

 Updated

0.70

 OnePlus

0.69

 Subtle

0.68

OUS

0.68

Activations Density 18.353%

personal names

No Comments

No Known Activations