INDEX

Explanations

terms related to historical and political ideologies

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

preceding "March," "Project," or describing empires

np_acts-logits-general · gemini-2.0-flash

Imperial and biblical history

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.81

tagHelperRunner

-0.71

__':

-0.64

 دیکھیے

-0.63

dollis

-0.61

esgue

-0.57

DECREF

-0.57

 MainAxisSize

-0.56

 ujednoznacz

-0.56

rzost

-0.56

POSITIVE LOGITS

era

0.73

rrggbb

0.63

Era

0.62

 period

0.60

Era

0.58

Parcelize

0.56

TIMES

0.56

 themed

0.55

 döne

0.55

 useParams

0.55

Activations Density 0.384%

terms related to historical and political ideologies

preceding "March," "Project," or describing empires

Imperial and biblical history

No Comments

No Known Activations