INDEX

Explanations

descriptions of historical events and locations

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

hess

-0.65

perty

-0.63

Contents

-0.62

limits

-0.58

Wide

-0.57

 challeng

-0.57

 psychiat

-0.57

Ô

-0.56

Response

-0.56

âľ

-0.56

POSITIVE LOGITS

 deceased

0.76

 fallen

0.67

 previous

0.66

 ancestral

0.61

 salv

0.61

 defunct

0.58

 Empires

0.58

old

0.57

 decom

0.56

 youth

0.56

Activations Density 14.944%

descriptions of historical events and locations

No Comments

No Known Activations