INDEX

Explanations

dates and locations

oai_token-act-pair · gpt-3.5-turbo

elements related to dates and numerical data

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

terness

-0.68

natureconservancy

-0.56

hetically

-0.55

idious

-0.54

 Flavoring

-0.54

 faire

-0.53

 hindsight

-0.53

itiveness

-0.51

Plot

-0.51

krit

-0.51

POSITIVE LOGITS

ĪĴ

0.64

aroo

0.60

ailable

0.57

 Wonderland

0.54

liga

0.53

foreseen

0.53

MQ

0.52

à¦

0.52

à¨

0.52

ailability

0.52

Activations Density 0.896%

dates and locations

elements related to dates and numerical data

No Comments

No Known Activations