INDEX

Explanations

phrases related to future intentions or strategies

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

anca

-0.68

int

-0.67

weed

-0.67

inton

-0.66

tha

-0.60

clad

-0.60

idge

-0.60

court

-0.60

aff

-0.60

cius

-0.59

POSITIVE LOGITS

 Parenthood

1.12

paren

0.78

 accordingly

0.75

¶

0.73

obs

0.72

escape

0.71

 pregnancies

0.69

§

0.68

ÄŁ

0.68

 regret

0.66

Activations Density 10.702%

phrases related to future intentions or strategies

No Comments

No Known Activations