INDEX

Explanations

mentions of political figures, political parties, and political systems

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

 Rica

-0.87

 Lovecraft

-0.80

 Gillespie

-0.78

 Canaver

-0.77

 Richards

-0.76

 Scotia

-0.75

 Lanka

-0.74

 Kafka

-0.74

BDS

-0.74

 Borders

-0.73

POSITIVE LOGITS

thirds

1.56

legged

1.52

year

1.48

dimensional

1.46

footed

1.40

tailed

1.38

sided

1.38

month

1.34

fif

1.34

digit

1.32

Activations Density 6.365%

mentions of political figures, political parties, and political systems

No Comments

No Known Activations