INDEX

Explanations

technical terms and specifications related to vehicles

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

Car models and editions

np_acts-logits-general · gemini-2.0-flash

car models and trims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ValueStyle

-1.02

 utafitiHapana

-0.75

MessageOf

-0.70

rrggbb

-0.69

UnsafeEnabled

-0.69

 ModelExpression

-0.66

 للاسماء

-0.65

Décès

-0.64

setVerticalGroup

-0.64

Билгалдахарш

-0.63

POSITIVE LOGITS

 series

0.66

 Series

0.61

Pro

0.57

II

0.57

 Edition

0.56

 phiên

0.56

 fitted

0.56

 version

0.55

series

0.55

Series

0.53

Activations Density 0.221%

technical terms and specifications related to vehicles

Car models and editions

car models and trims

No Comments

No Known Activations