INDEX

Explanations

phrases related to political figures and events

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

ĸļ

-0.59

nyder

-0.55

iland

-0.55

 guide

-0.54

 lest

-0.54

etsk

-0.54

angible

-0.53

aim

-0.52

jc

-0.52

zsche

-0.52

POSITIVE LOGITS

ioxide

0.83

arte

0.82

ADRA

0.79

 Skydragon

0.68

ottesville

0.68

ILLE

0.68

¥µ

0.67

ificial

0.67

otta

0.67

artist

0.66

Activations Density 1.207%

phrases related to political figures and events

No Comments

No Known Activations