INDEX

Explanations

commands and code snippets related to software development

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

CLASSIFIED

-0.76

llor

-0.76

HAEL

-0.73

 whistleblowers

-0.69

 incumb

-0.66

ens

-0.66

 Hait

-0.65

 Carlton

-0.64

 contag

-0.64

ileaks

-0.64

POSITIVE LOGITS

 lieu

1.33

 conjunction

1.32

 accordance

1.25

animate

1.22

 addition

1.18

 unison

1.13

clusions

1.12

 order

1.10

ordinate

1.08

 relation

1.06

Activations Density 7.695%

commands and code snippets related to software development

No Comments

No Known Activations