INDEX

Explanations

mentions of specific names, dates or 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

awar

-0.93

asonic

-0.89

apping

-0.83

iddles

-0.79

aiman

-0.79

idges

-0.77

agonists

-0.75

 disadvant

-0.75

ighed

-0.74

itaire

-0.72

POSITIVE LOGITS

Ĺ

0.97

é»Ĵ

0.95

lishing

0.95

ï¸ı

0.92

gers

0.89

lish

0.89

ãĥ¬

0.86

æĸ¹

0.84

ging

0.83

RAM

0.83

Activations Density 7.321%

mentions of specific names, dates or locations

No Comments

No Known Activations