INDEX

Explanations

references to military units, personnel, and organizational structures

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

acious

-0.88

 guiActiveUn

-0.86

arching

-0.80

hod

-0.79

itching

-0.73

aciously

-0.73

itely

-0.72

essage

-0.69

iscopal

-0.69

ifying

-0.69

POSITIVE LOGITS

Ltd

0.79

 Massacre

0.78

ptives

0.78

 Limited

0.74

 Reports

0.74

 Publishers

0.73

 Fathers

0.72

 Ships

0.72

uria

0.70

 Hath

0.68

Activations Density 8.506%

references to military units, personnel, and organizational structures

No Comments

No Known Activations