INDEX

Explanations

instances of legal or criminal terminology and actions related to violence

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

Followed by "by"

np_acts-logits-general · gemini-2.0-flash

recruited by, attacked by, given by

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

()?;

-0.64

 cref

-0.63

MemoryWarning

-0.56

elements

-0.54

RetentionPolicy

-0.54

 tartalomajánló

-0.54

 OFDb

-0.54

zzar

-0.53

endregion

-0.52

rawDesc

-0.52

POSITIVE LOGITS

by

0.63

 oleh

0.59

 przez

0.57

 served

0.52

MLLoader

0.52

 byen

0.52

 diminta

0.51

vantaged

0.51

 opérés

0.50

 Hague

0.49

Activations Density 0.522%

instances of legal or criminal terminology and actions related to violence

Followed by "by"

recruited by, attacked by, given by

No Comments

No Known Activations