INDEX

Explanations

instances of pride or accomplishment expressed in text

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

apter

-0.82

PF

-0.80

itamin

-0.73

ondo

-0.72

ential

-0.72

pmwiki

-0.71

 Webster

-0.70

vati

-0.68

amber

-0.66

riminal

-0.66

POSITIVE LOGITS

edly

1.01

hon

0.90

edIn

0.88

roud

0.84

faced

0.80

gow

0.80

lete

0.78

ful

0.77

castle

0.76

fully

0.74

Activations Density 7.425%

instances of pride or accomplishment expressed in text

No Comments

No Known Activations