INDEX

Explanations

sentences related to personal integrity and physical safety

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

NetMessage

-0.74

INO

-0.73

ãĤ´ãĥ³

-0.71

MpServer

-0.70

akia

-0.69

shall

-0.68

aukee

-0.68

INA

-0.67

zie

-0.66

milo

-0.65

POSITIVE LOGITS

iest

1.10

ourge

0.89

of

0.83

liest

0.77

 portion

0.75

forts

0.75

 playbook

0.72

 aspect

0.72

quo

0.68

 ethic

0.68

Activations Density 9.220%

sentences related to personal integrity and physical safety

No Comments

No Known Activations