INDEX

Explanations

references to specific locations or events often related to politics or military interventions

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

Mods

-0.75

 hostilities

-0.71

 Haku

-0.71

 Reload

-0.68

 trolling

-0.65

Rin

-0.64

 Harding

-0.62

 Difference

-0.62

Category

-0.62

 Baal

-0.61

POSITIVE LOGITS

Gov

0.89

 WATCHED

0.88

ldon

0.86

Os

0.81

Interstitial

0.81

azeera

0.80

[-

0.79

 underestimate

0.79

Ã±

0.79

cam

0.78

Activations Density 20.410%

references to specific locations or events often related to politics or military interventions

No Comments

No Known Activations