INDEX

Explanations

terms related to user privacy and data handling

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

legal and technical jargon

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

 democrática

-0.49

 legales

-0.48

 métiers

-0.44

 Drummond

-0.44

 boneka

-0.42

 judiciales

-0.41

 inalámbrica

-0.40

 animación

-0.39

 Schnell

-0.39

 democracia

-0.39

POSITIVE LOGITS

 Italijanski

0.85

parsedMessage

0.76

 Савезне

0.74

хьтан

0.73

SharedDtor

0.70

цездатний

0.69

 nahilalakip

0.67

 ویکی‌پدی

0.67

 unknownFields

0.65

Jeografia

0.64

Activations Density 0.014%

terms related to user privacy and data handling

legal and technical jargon

No Comments

No Known Activations