INDEX

Explanations

references or mentions of media outlets or organizations' names

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

proper nouns and specific organizational names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

SPA

-0.70

%%%%

-0.66

bys

-0.65

uj

-0.64

nyder

-0.62

bnb

-0.61

wat

-0.60

cart

-0.60

axis

-0.60

spons

-0.59

POSITIVE LOGITS

 GEAR

0.73

ICAN

0.68

¢

0.65

azon

0.65

Ķ

0.65

ITED

0.65

oline

0.61

 Dakota

0.60

olated

0.59

 Down

0.58

Activations Density 0.222%

references or mentions of media outlets or organizations' names

proper nouns and specific organizational names

No Comments

No Known Activations