INDEX

Explanations

documents that discuss identity and identification, particularly in the context of projects or individuals being identified or differentiated from others

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

uden

-0.73

zzo

-0.69

 Bakr

-0.64

avorite

-0.64

 Pigs

-0.63

 Laksh

-0.61

 arsen

-0.61

UGH

-0.58

 Ramsey

-0.58

Ļ½

-0.57

POSITIVE LOGITS

ifier

1.06

ifiers

1.05

ifications

1.00

ifiable

0.99

itarian

0.95

ifying

0.93

ãĤ©

0.85

ities

0.85

idad

0.83

ifies

0.83

Activations Density 6.731%

documents that discuss identity and identification, particularly in the context of projects or individuals being identified or differentiated from others

No Comments

No Known Activations