INDEX

Explanations

words related to legal issues and governmental actions, particularly focusing on policies, decisions, and perspectives involving various branches of law and government

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

faced

-0.98

hyde

-0.84

ierrez

-0.83

ridges

-0.83

agy

-0.83

aqu

-0.82

aca

-0.81

hai

-0.80

sic

-0.78

busters

-0.78

POSITIVE LOGITS

 afar

1.74

 whence

1.35

 thence

1.19

 scratch

1.13

 abroad

1.02

 inception

1.01

 inside

0.99

 within

0.98

 anywhere

0.97

 elsewhere

0.95

Activations Density 7.726%

words related to legal issues and governmental actions, particularly focusing on policies, decisions, and perspectives involving various branches of law and government

No Comments

No Known Activations