INDEX

Explanations

references to nationalism and related ideologies

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Oracle

-0.68

OME

-0.65

neau

-0.65

EVA

-0.64

ĸļ

-0.63

lift

-0.62

nesota

-0.61

 Thumbnails

-0.61

err

-0.60

Tree

-0.60

POSITIVE LOGITS

 sentiments

0.74

 ferv

0.70

 pride

0.69

 sentiment

0.63

 nationalist

0.63

 rhetoric

0.61

 popul

0.61

 nationalism

0.61

vis

0.59

 zeal

0.59

Activations Density 8.502%

references to nationalism and related ideologies

No Comments

No Known Activations