INDEX

Explanations

references to Native Americans, Indigenous tribes, Native culture, and related historical and contemporary topics

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

utenberg

-0.89

tered

-0.81

acies

-0.79

abl

-0.78

oldemort

-0.73

 reper

-0.70

inventoryQuantity

-0.69

adden

-0.69

-+-+

-0.69

ilton

-0.69

POSITIVE LOGITS

 Sioux

0.97

 Instruments

0.96

 Hawaiian

0.96

 Hawai

0.94

 tribes

0.94

 Peoples

0.93

 tribe

0.91

 Native

0.90

 Tribe

0.90

 Navajo

0.88

Activations Density 9.530%

references to Native Americans, Indigenous tribes, Native culture, and related historical and contemporary topics

No Comments

No Known Activations