INDEX

Explanations

positive sentiment and friendly interactions

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

ĨĴ

-0.78

geant

-0.74

hran

-0.67

»Ĵ

-0.66

 IMAGES

-0.65

 Phant

-0.62

ãĤ¼

-0.60

ãĤ®

-0.59

xiety

-0.58

*/(

-0.58

POSITIVE LOGITS

 cord

1.08

lessly

1.02

 Cord

0.95

oba

0.78

 cords

0.78

ovan

0.73

elo

0.71

elia

0.69

iously

0.69

wood

0.68

Activations Density 5.949%

positive sentiment and friendly interactions

No Comments

No Known Activations