INDEX

Explanations

enumeration and structure in written content

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

ordering or listing items

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

 sitten

-0.40

StoryboardSegue

-0.40

 concluye

-0.40

olarmente

-0.40

 libremente

-0.40

 intereses

-0.39

 işte

-0.39

escudo

-0.38

 conclusiones

-0.37

 ayudas

-0.37

POSITIVE LOGITS

 Signalez

0.61

 للاسماء

0.56

//

0.55

 <<<<<<<<<<<<<<

0.55

 ویکی‌پدی

0.53

EDEFAULT

0.48

oa̍t

0.47

﹠

0.43

IsMutable

0.42

Activations Density 0.021%

enumeration and structure in written content

ordering or listing items

No Comments

No Known Activations