INDEX

Explanations

the word "but" and pronouns that directly follow "but"

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 balanceOf

-0.54

 namelijk

-0.54

Ữ

-0.53

 springfox

-0.53

(;;)

-0.50

التالي

-0.50

validates

-0.50

GetHashCode

-0.49

 useDispatch

-0.49

เลย

-0.49

POSITIVE LOGITS

 nevertheless

1.35

 nonetheless

1.27

terscotch

1.05

 dennoch

0.98

chery

0.95

chers

0.91

 alas

0.90

 néanmoins

0.89

 digress

0.82

 ändå

0.82

Activations Density 0.826%

the word "but" and pronouns that directly follow "but"

No Comments

No Known Activations