INDEX

Explanations

references to military units, militias, villages, and communities within a narrative context

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

henko

-0.90

pter

-0.77

inventoryQuantity

-0.76

umbn

-0.75

ï¸

-0.75

nyder

-0.73

————————————————

-0.71

zona

-0.71

ocaust

-0.70

ulative

-0.70

POSITIVE LOGITS

 villages

0.91

 village

0.86

folk

0.83

 Adin

0.79

 kitchens

0.75

 Village

0.75

hood

0.74

 elders

0.73

 outpost

0.72

 Shal

0.72

Activations Density 6.046%

references to military units, militias, villages, and communities within a narrative context

No Comments

No Known Activations