INDEX

Explanations

the word "turn" followed by a number indicating a significant action or change

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¦ļéĨĴ

-1.05

ropolitan

-0.92

capacity

-0.82

mma

-0.80

inately

-0.78

ording

-0.76

foundation

-0.72

bour

-0.71

llah

-0.71

lain

-0.69

POSITIVE LOGITS

awa

0.87

 into

0.85

coat

0.81

 shif

0.77

agra

0.76

around

0.76

 inward

0.75

 crank

0.75

about

0.75

 sour

0.74

Activations Density 8.651%

the word "turn" followed by a number indicating a significant action or change

No Comments

No Known Activations