INDEX

Explanations

phrases and terms related to tragic events and mourning

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

bones

-0.63

nect

-0.60

ãĥ©

-0.53

xual

-0.53

artney

-0.53

 veins

-0.52

hered

-0.51

poke

-0.50

 cooker

-0.50

APTER

-0.50

POSITIVE LOGITS

arty

0.80

atis

0.68

adium

0.68

aque

0.67

ghai

0.66

acco

0.64

itsch

0.63

ning

0.63

zon

0.61

atu

0.60

Activations Density 9.303%

phrases and terms related to tragic events and mourning

No Comments

No Known Activations