INDEX

Explanations

medical and health-related terms and discussions

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

 embr

-1.03

oil

-1.01

yrights

-0.92

assetsadobe

-0.91

pmwiki

-0.90

atron

-0.90

 Bounce

-0.89

asonic

-0.88

 cove

-0.88

Bit

-0.87

POSITIVE LOGITS

 clinical

1.33

 cohort

1.32

 maternal

1.25

 Clinical

1.21

 enrolled

1.19

 psychiatric

1.18

 questionnaire

1.17

 clinically

1.16

 Patient

1.16

 Patients

1.15

Activations Density 9.950%

medical and health-related terms and discussions

No Comments

No Known Activations