INDEX

Explanations

elements and attributes commonly used in HTML or XML formatting

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

HTML option tags or similar dropdown choices

np_acts-logits-general · gemini-2.0-flash

available options or choices

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

+#+#

-0.73

MemoryWarning

-0.68

awtextra

-0.62

@"/

-0.61

şiv

-0.61

 ModelExpression

-0.59

parsedMessage

-0.58

SourceChecksum

-0.57

 CanadaChoose

-0.57

utilisons

-0.57

POSITIVE LOGITS

 available

0.45

 selections

0.44

 disponibile

0.43

 options

0.42

 dostępne

0.41

 disponibles

0.40

 dostup

0.40

 choices

0.39

available

0.39

Available

0.39

Activations Density 0.118%

elements and attributes commonly used in HTML or XML formatting

HTML option tags or similar dropdown choices

available options or choices

No Comments

No Known Activations