INDEX

Explanations

components related to data structure definitions and attachments in programming

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

HTML or code attributes/tags/headers

np_acts-logits-general · gemini-2.0-flash

additional information

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LookAnd

-0.55

 виправивши

-0.53

 مشين

-0.52

ClassNotFound

-0.50

Izvori

-0.50

 الأصل

-0.49

Према

-0.48

̸

-0.47

NegativeButton

-0.47

velt

-0.47

POSITIVE LOGITS

 also

0.95

rrggbb

0.76

also

0.73

 alſo

0.72

 também

0.68

 juga

0.68

 additionally

0.67

 también

0.67

 inoltre

0.66

 همچنین

0.64

Activations Density 0.099%

components related to data structure definitions and attachments in programming

HTML or code attributes/tags/headers

additional information

No Comments

No Known Activations