INDEX

Explanations

markup tags and elements in a document

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

XML or code-like syntax

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-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

TestingModule

-0.67

PreferredItem

-0.65

WidgetItem

-0.59

 createSprite

-0.59

Personensuche

-0.58

EDEFAULT

-0.55

月号

-0.53

#+#

-0.53

ngdoc

-0.51

issier

-0.51

POSITIVE LOGITS

 typelib

0.74

[toxicity=0]

0.65

GOTREF

0.59

</s>

0.52

principalTable

0.51

0.50

0.49

APORE

0.48

Hochspringen

0.47

?>">

0.47

Activations Density 0.648%

markup tags and elements in a document

XML or code-like syntax

HTML/XML tags and attributes

No Comments

No Known Activations