INDEX

Explanations

mentions of the term "vin" in various contexts related to people, places, or substances

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

Tokens starting with "Vin" or "Win"

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 Etats

-0.35

 paik

-0.35

 vectorielle

-0.34

 eletrônico

-0.33

 Majefty

-0.33

tgärder

-0.32

 ſtate

-0.31

 môn

-0.30

 şeker

-0.30

course

-0.30

POSITIVE LOGITS

 للاسماء

0.78

Win

0.76

Win

0.76

win

0.75

win

0.70

 فريبيس

0.69

WIN

0.66

WIN

0.66

Vin

0.66

Vin

0.65

Activations Density 0.062%

mentions of the term "vin" in various contexts related to people, places, or substances

Tokens starting with "Vin" or "Win"

No Comments

No Known Activations