INDEX

Explanations

HTML form attributes and elements

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

HTML attribute values within quotation marks

np_acts-logits-general · gemini-2.0-flash

HTML/XML tags and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 &___

-0.52

 resourceCulture

-0.51

 TextAppearance

-0.50

 esternos

-0.50

Portály

-0.49

ImageContext

-0.47

 ſtate

-0.47

########.

-0.46

 eſt

-0.45

 للاسماء

-0.45

POSITIVE LOGITS

 Borja

0.50

 Schar

0.42

 include

0.42

 assigned

0.41

itattu

0.41

 Duggan

0.39

 Spiegel

0.39

__*/

0.39

 heard

0.39

 colspan

0.39

Activations Density 0.143%

HTML form attributes and elements

HTML attribute values within quotation marks

HTML/XML tags and attributes

No Comments

No Known Activations