INDEX

Explanations

mentions of wrestling participants and their accomplishments, along with broader sports analysis.

oai_token-act-pair · gemini-2.0-flash

Forms of "to be"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<%=

-0.47

 asesin

-0.45

 externi

-0.45

={<

-0.45

 UPDATED

-0.43

 geholfen

-0.42

 reçu

-0.42

=<?

-0.41

careers

-0.41

won

-0.41

POSITIVE LOGITS

 ویکی‌پدی

0.70

GOTREF

0.70

adpleegd

0.66

addCriterion

0.65

webElementXpaths

0.65

 Roskov

0.64

 pinulongan

0.63

:✨

0.63

IVEREF

0.63

 Pristupljeno

0.63

Activations Density 0.641%

mentions of wrestling participants and their accomplishments, along with broader sports analysis.

Forms of "to be"

No Comments

No Known Activations