INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people and potential entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

idth

-0.62

lihood

-0.62

vironment

-0.60

berra

-0.57

 âĢº

-0.57

ä»£

-0.56

ãĤ´ãĥ³

-0.55

Benz

-0.54

mble

-0.54

chel

-0.53

POSITIVE LOGITS

rul

0.63

yang

0.60

ModLoader

0.52

 detractors

0.52

 himself

0.51

FFER

0.50

 herself

0.50

 muse

0.50

fal

0.49

 palate

0.49

Activations Density 0.733%

proper nouns

proper nouns, specifically names of people and potential entities

No Comments

No Known Activations