INDEX

Explanations

dates in various formats

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stead

-0.74

hed

-0.67

ess

-0.65

esses

-0.64

lass

-0.56

kell

-0.56

phy

-0.55

amn

-0.55

ournals

-0.54

nut

-0.54

POSITIVE LOGITS

å¹

1.17

-'

0.72

âĢ²

0.71

0.69

 Edition

0.65

 edition

0.65

 vintage

0.65

 Nobel

0.62

 onwards

0.61

 EDITION

0.60

Activations Density 13.146%

dates in various formats

No Comments

No Known Activations