INDEX

Explanations

mentions of military ranks and law enforcement titles

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

ahime

-0.95

theless

-0.88

rights

-0.79

FORE

-0.70

GPU

-0.69

OPA

-0.69

topic

-0.67

trak

-0.66

bull

-0.66

phal

-0.65

POSITIVE LOGITS

geant

1.21

Sgt

1.08

 Sergeant

0.97

Maj

0.89

Lt

0.84

 Pepper

0.82

gt

0.81

 sergeant

0.81

 Lance

0.80

chief

0.79

Activations Density 5.887%

mentions of military ranks and law enforcement titles

No Comments

No Known Activations