INDEX

Explanations

mentions of US states or laws related to states, especially in the context of federal government, legislation, and policies

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

 Pastebin

-0.67

sett

-0.67

rious

-0.64

 Domain

-0.63

 Lect

-0.62

ADS

-0.61

 Nose

-0.61

Rocket

-0.60

RTX

-0.59

SPL

-0.58

POSITIVE LOGITS

manship

1.27

men

1.03

man

0.89

rooms

0.87

 legislatures

0.85

ide

0.83

hips

0.78

chool

0.76

 legalizing

0.75

states

0.75

Activations Density 5.708%

mentions of US states or laws related to states, especially in the context of federal government, legislation, and policies

No Comments

No Known Activations