INDEX

Explanations

phrases related to violent or illegal actions, specifically those categorized as terrorism

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

 corners

-0.82

 ceilings

-0.71

 edges

-0.69

 Flavoring

-0.62

 walls

-0.62

 facets

-0.61

 Wheat

-0.60

 Pyramid

-0.58

devices

-0.58

ernels

-0.58

POSITIVE LOGITS

 luck

0.82

 sabotage

0.81

 kindness

0.76

 omission

0.74

OUP

0.71

asses

0.68

 heroism

0.68

EVA

0.66

 desperation

0.65

ACTION

0.64

Activations Density 9.943%

phrases related to violent or illegal actions, specifically those categorized as terrorism

No Comments

No Known Activations