INDEX

Explanations

medical terms and concepts related to clinical trials and healthcare

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

 Sabha

-0.73

TAG

-0.68

 Closed

-0.68

Merit

-0.66

 disadvant

-0.66

Prince

-0.64

ashtra

-0.63

 Blossom

-0.61

 stakes

-0.59

éŃĶ

-0.59

POSITIVE LOGITS

itory

0.79

ndum

0.77

itte

0.75

vernment

0.74

itely

0.72

glers

0.71

ibly

0.71

ascript

0.68

ruary

0.67

alion

0.67

Activations Density 13.597%

medical terms and concepts related to clinical trials and healthcare

No Comments

No Known Activations