INDEX

Explanations

medical procedures and processes outlined in detailed descriptions

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

minster

-0.84

bitious

-0.78

gets

-0.78

hab

-0.74

 Flavoring

-0.72

ku

-0.71

agi

-0.68

inese

-0.66

aez

-0.65

vill

-0.64

POSITIVE LOGITS

 procedure

0.88

 procedures

0.81

DragonMagazine

0.71

 droid

0.70

 Inqu

0.69

 manuals

0.69

 Procedure

0.67

ional

0.67

 Procedures

0.67

 manual

0.67

Activations Density 5.733%

medical procedures and processes outlined in detailed descriptions

No Comments

No Known Activations