INDEX

Explanations

time-related phrases, particularly ones denoting a shorter time duration

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

hran

-0.88

olitan

-0.86

ieri

-0.83

alogy

-0.81

olis

-0.79

itiz

-0.77

odium

-0.74

ulet

-0.73

iom

-0.72

ilon

-0.72

POSITIVE LOGITS

 half

0.87

 halfway

0.79

 stellar

0.78

 cents

0.76

 expected

0.75

 satisfactory

0.72

 ideal

0.71

Â½

0.70

 Â½

0.69

capacity

0.69

Activations Density 10.608%

time-related phrases, particularly ones denoting a shorter time duration

No Comments

No Known Activations