INDEX

Explanations

code snippets related to software development, particularly focusing on initializing variables, building components, and defining functions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

 AIDS

-1.02

 starvation

-0.99

 ashes

-0.96

Twitter

-0.94

cancer

-0.92

âĢİ

-0.92

 Depression

-0.92

 hurting

-0.92

Bull

-0.91

AIDS

-0.91

POSITIVE LOGITS

 assume

1.18

 configure

1.17

ird

1.16

 setup

1.16

iago

1.13

Ã¡s

1.13

yip

1.10

 simplify

1.10

brance

1.09

 interpol

1.09

Activations Density 2.465%

code snippets related to software development, particularly focusing on initializing variables, building components, and defining functions

No Comments

No Known Activations