INDEX

Explanations

references to dishonesty or deceit

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

aldi

-1.00

ISO

-0.99

ains

-0.94

orsi

-0.90

okemon

-0.89

ategory

-0.88

iles

-0.87

FN

-0.86

allows

-0.86

obs

-0.85

POSITIVE LOGITS

 detector

1.26

uten

1.25

utenant

1.25

bling

1.05

 detectors

1.01

 dormant

1.01

 vulner

0.98

ge

0.95

half

0.93

 theoret

0.92

Activations Density 0.667%

references to dishonesty or deceit

No Comments

No Known Activations