INDEX

Explanations

the word "intelligent" or variations of it

oai_token-act-pair · gpt-3.5-turbo

references to intelligence or intelligent entities and their characteristics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thur

-0.83

MY

-0.75

ween

-0.73

soDeliveryDate

-0.72

rine

-0.71

esville

-0.71

bered

-0.68

eters

-0.68

abies

-0.68

laus

-0.68

POSITIVE LOGITS

elligent

1.03

 beings

0.94

 intelligent

0.94

 intellig

0.89

 quot

0.83

Reviewer

0.81

 Intelligent

0.76

 autom

0.73

 enough

0.73

 minded

0.71

Activations Density 0.027%

the word "intelligent" or variations of it

references to intelligence or intelligent entities and their characteristics

No Comments

No Known Activations