INDEX

Explanations

terms related to elections and voter fraud

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

elections and voters

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

 aktif

-0.54

 saluti

-0.54

 MainAxisSize

-0.52

참고

-0.50

CrossRef

-0.49

Growth

-0.49

 growth

-0.49

 StringTokenizer

-0.46

 abbigliamento

-0.46

 zoek

-0.45

POSITIVE LOGITS

 Electoral

0.91

 electoral

0.89

 Election

0.84

 Elections

0.79

Election

0.74

 ballot

0.71

 voter

0.70

 للاسماء

0.69

 election

0.69

 Voter

0.69

Activations Density 0.106%

terms related to elections and voter fraud

elections and voters

No Comments

No Known Activations