INDEX

Explanations

references and quotes from news articles, particularly those related to government actions and political figures

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

tty

-0.77

gone

-0.73

course

-0.72

xual

-0.71

pants

-0.69

gaard

-0.68

 ment

-0.66

lift

-0.64

changed

-0.64

abiding

-0.63

POSITIVE LOGITS

TN

1.09

PLE

0.95

PLIED

0.94

PLA

0.92

OE

0.90

PLIC

0.90

 Photo

0.84

PROV

0.84

ocalypse

0.84

osta

0.83

Activations Density 3.161%

references and quotes from news articles, particularly those related to government actions and political figures

No Comments

No Known Activations