INDEX

Explanations

items related to health and medical terminology

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

terms related to legal and official matters

oai_token-act-pair · gpt-3.5-turbo

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

lua

-0.54

 oats

-0.53

 pies

-0.52

bows

-0.50

chenko

-0.48

 grapes

-0.48

 pudding

-0.48

 biscuits

-0.47

 Cree

-0.47

 Niet

-0.46

POSITIVE LOGITS

merce

0.56

Joined

0.52

IBLE

0.51

lesiastical

0.48

lisher

0.47

MENT

0.47

 guiIcon

0.47

priv

0.47

 Regulations

0.46

ATURE

0.46

Activations Density 0.248%

items related to health and medical terminology

terms related to legal and official matters

No Comments

No Known Activations