INDEX

Explanations

instances of the word 'auto' indicating automatic styles in CSS

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

auto property

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 prohibido

-0.51

 extranjera

-0.45

 enamorado

-0.43

 helicóptero

-0.42

 contratación

-0.41

 coordinación

-0.41

šanās

-0.41

 húmedo

-0.40

 infraestructura

-0.40

 continuidad

-0.40

POSITIVE LOGITS

 auto

1.71

auto

1.45

 Auto

1.40

Auto

1.27

 AUTO

1.22

ChildScrollView

1.11

 autos

1.08

AUTO

1.02

 авто

0.94

 autob

0.92

Activations Density 0.001%

instances of the word 'auto' indicating automatic styles in CSS

auto property

No Comments

No Known Activations