INDEX

Explanations

medical institutions and facilities

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

posted

-0.60

inventoryQuantity

-0.58

written

-0.57

IBLE

-0.56

yt

-0.56

 rage

-0.54

ibilities

-0.52

hered

-0.52

xual

-0.52

ebook

-0.52

POSITIVE LOGITS

 Association

0.80

 Sciences

0.79

 Complex

0.75

 Library

0.75

 Authority

0.73

 Solutions

0.73

 Massacre

0.73

 Majority

0.73

 Laboratory

0.70

 Conference

0.70

Activations Density 6.357%

medical institutions and facilities

No Comments

No Known Activations