INDEX

Explanations

food-related terms, especially specific dishes or ingredients

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

Dialogue

-0.81

 Democr

-0.75

 Templ

-0.73

CTV

-0.69

FORE

-0.69

ALE

-0.68

Jol

-0.66

Charges

-0.66

 Degree

-0.65

ige

-0.65

POSITIVE LOGITS

enegger

1.21

ming

1.21

intosh

0.99

tops

0.91

opian

0.90

bles

0.88

berries

0.88

eting

0.87

inx

0.86

rador

0.85

Activations Density 6.952%

food-related terms, especially specific dishes or ingredients

No Comments

No Known Activations