INDEX

Explanations

references to going beyond the usual or expected boundaries or standards

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

 largeDownload

-0.73

 followed

-0.71

MpServer

-0.70

soType

-0.70

 Stacy

-0.68

PsyNetMessage

-0.68

dayName

-0.67

 alike

-0.65

————

-0.65

enos

-0.65

POSITIVE LOGITS

 confines

1.21

 bounds

1.17

 borders

1.07

 boundaries

1.06

 limits

1.06

 scope

1.01

 limitations

0.94

 usual

0.93

 walls

0.87

 limitation

0.82

Activations Density 10.299%

references to going beyond the usual or expected boundaries or standards

No Comments

No Known Activations