INDEX

Explanations

phrases and actions related to user interactions with menus and buttons

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

Comes before actions ("to [verb]")

np_acts-logits-general · gemini-2.0-flash

to activate

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

twimg

-0.53

 struggled

-0.48

BrowserModule

-0.47

льтра

-0.47

きている

-0.44

StatusCode

-0.42

 spolup

-0.42

 erreurs

-0.42

 cliquant

-0.42

 communautaire

-0.41

POSITIVE LOGITS

 activate

0.81

 activates

0.80

 activating

0.80

 access

0.79

下载附件

0.76

 instantly

0.75

 triggering

0.71

Personendaten

0.70

 trigger

0.69

 reveal

0.68

Activations Density 0.350%

phrases and actions related to user interactions with menus and buttons

Comes before actions ("to [verb]")

to activate

No Comments

No Known Activations