INDEX

Explanations

instructions or actions that involve clicking or selecting items within a user interface

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

Preceding a link or selection

np_acts-logits-general · gemini-2.0-flash

click/select followed by noun/preposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

دانشنامهٔ

-0.69

 חיצוניים

-0.63

LookAnd

-0.62

 considérons

-0.59

 للمعارف

-0.58

NSUserDefaults

-0.58

 препратки

-0.57

 المعيارى

-0.55

 ligiloj

-0.55

googleapis

-0.54

POSITIVE LOGITS

SuppressLint

0.56

 blue

0.52

 héri

0.52

 zelen

0.52

astéroïdes

0.52

camiseta

0.51

 quelcon

0.49

blue

0.48

 amarelo

0.48

 anything

0.48

Activations Density 0.107%

instructions or actions that involve clicking or selecting items within a user interface

Preceding a link or selection

click/select followed by noun/preposition

No Comments

No Known Activations