INDEX

Explanations

medical terms and terminology relating to legal contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĶ°

-0.78

anwhile

-0.75

 Kenyan

-0.70

 reception

-0.69

 cyan

-0.67

 scattering

-0.67

lder

-0.67

Roc

-0.66

 snail

-0.63

mid

-0.62

POSITIVE LOGITS

Â¯

1.00

į

0.95

¬

0.91

âĹ¼

0.87

ı

0.85

0.84

º

0.81

âĢł

0.79

Ĵ

0.78

_.

0.78

Activations Density 11.105%

medical terms and terminology relating to legal contexts

No Comments

No Known Activations