INDEX

Explanations

statistical terms and procedures, especially those related to data analysis and significance testing

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

lain

-0.83

aline

-0.66

egg

-0.65

shire

-0.65

nen

-0.61

xia

-0.60

eem

-0.59

 Corinthians

-0.57

igans

-0.57

Khe

-0.55

POSITIVE LOGITS

istically

0.95

istical

0.82

oster

0.67

 significance

0.66

istics

0.64

istic

0.61

inately

0.60

analysis

0.59

 Mehran

0.58

iler

0.58

Activations Density 0.374%

statistical terms and procedures, especially those related to data analysis and significance testing

No Comments

No Known Activations