INDEX

Explanations

references to rules or restrictions in a legal or formal context

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

Mathematical or symbolic representations

np_acts-logits-general · gemini-2.0-flash

give up

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Brito

-0.64

şiv

-0.57

forRoot

-0.57

principalColumn

-0.55

 createSprite

-0.55

ListItemIcon

-0.54

колай

-0.54

//

-0.54

 خارجية

-0.53

ZoneId

-0.53

POSITIVE LOGITS

 propOrder

0.70

ldots

0.70

IVEREF

0.55

}{$\

0.53

bux

0.52

principalTable

0.51

 anatomy

0.49

Bum

0.48

AutoField

0.48

бочки

0.46

Activations Density 0.048%

references to rules or restrictions in a legal or formal context

Mathematical or symbolic representations

give up

No Comments

No Known Activations