INDEX

Explanations

references to legislative bills and proposed laws

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

Ti

-0.62

 Chal

-0.61

eyed

-0.58

ception

-0.57

Inst

-0.57

VM

-0.56

Statistics

-0.56

Case

-0.56

 Neph

-0.56

 Sung

-0.55

POSITIVE LOGITS

be

0.86

 doubtless

0.83

 deepen

0.82

 introduce

0.81

 revive

0.81

 allow

0.81

 dismantle

0.81

 reopen

0.81

 seek

0.80

 likely

0.79

Activations Density 13.444%

references to legislative bills and proposed laws

No Comments

No Known Activations