INDEX

Explanations

references to code structures and programming functions

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

HTML tags and attributes

np_acts-logits-general · gemini-2.0-flash

page names or links

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

HasAnnotation

-0.49

 téléphonique

-0.47

="{{$

-0.46

Abitanti

-0.45

 rowspan

-0.41

这项

-0.39

disfraz

-0.38

 beno

-0.38

BoxShadow

-0.37

 Wicidata

-0.37

POSITIVE LOGITS

 home

1.38

 homepage

1.25

home

1.25

 Home

1.22

Home

1.20

 HOME

1.14

 HomePage

1.13

 dashboard

1.11

 welcome

1.10

welcome

1.08

Activations Density 0.199%

references to code structures and programming functions

HTML tags and attributes

page names or links

No Comments

No Known Activations