INDEX

Explanations

instances of administrative processes and documentation

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

documents submitted or returned

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Tembelea

-0.59

EndGlobalSection

-0.57

transQ

-0.56

AsUp

-0.51

ViewImports

-0.50



-0.47

ABULARY

-0.46

Personensuche

-0.46

 memberId

-0.44

 contextLoads

-0.43

POSITIVE LOGITS

 submitted

0.52

sidemargin

0.50

 submitting

0.46

 signé

0.45

 submit

0.43

 promptly

0.42

 yanı

0.41

 Submitted

0.40

 quedarse

0.40

submitted

0.39

Activations Density 0.008%

instances of administrative processes and documentation

documents submitted or returned

No Comments

No Known Activations