INDEX

Explanations

words related to space missions and projects, such as spacecraft names, mission phases, and journey descriptions

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

ãģį

-0.82

picking

-0.82

Column

-0.78

 Ange

-0.75

weak

-0.72

urrency

-0.71

amera

-0.70

Prev

-0.68

tery

-0.68

batch

-0.67

POSITIVE LOGITS

eers

0.97

 missions

0.92

arily

0.91

 Impossible

0.89

 mission

0.88

 creep

0.88

 undertaken

0.85

 accomplished

0.83

Vie

0.80

 abroad

0.80

Activations Density 4.021%

words related to space missions and projects, such as spacecraft names, mission phases, and journey descriptions

No Comments

No Known Activations