INDEX

Explanations

descriptions of physical confrontations and battles

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

 Borders

-1.02

adequ

-0.91

 Lieberman

-0.86

ylum

-0.83

 amen

-0.81

 Palestin

-0.80

 Surviv

-0.79

ĻĤ

-0.78

 McCann

-0.77

 Dwell

-0.76

POSITIVE LOGITS

 blasts

1.21

 volley

1.21

ulic

1.19

 pulses

1.12

 cannons

1.08

 cannon

1.05

 force

1.05

 bursts

1.04

 pumps

1.03

 piston

1.02

Activations Density 3.695%

descriptions of physical confrontations and battles

No Comments

No Known Activations