INDEX

Explanations

mentions of political figures and entities, particularly related to investigations and controversies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 bearing

-0.49

 interessiert

-0.48

DeleteBehavior

-0.48

 comp

-0.46

sup

-0.46

 поза

-0.46

getOriginal

-0.45

comp

-0.44

Comp

-0.44

str

-0.43

POSITIVE LOGITS

transQ

0.70

kháu

0.66

lusconi

0.64

rungsseite

0.63

">//

0.61

,:,

0.60

expandindo

0.58

 للاسماء

0.58

WebElementEntity

0.57

 hObject

0.56

Activations Density 0.295%

mentions of political figures and entities, particularly related to investigations and controversies

No Comments

No Known Activations