INDEX

Explanations

HTML comment tags in the text

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

HTML or XML code sequences

np_acts-logits-general · gemini-2.0-flash

HTML comments and DOCTYPE

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

brainly

-0.90

InjectAttribute

-0.82

 BorderSide

-0.78

richTextPanel

-0.77

 FetchType

-0.76

 pylint

-0.75

 MonoBehaviour

-0.74

TintMode

-0.73

HtmlAttribute

-0.73

 onResponse

-0.72

POSITIVE LOGITS

End

0.69

 begin

0.62

 Start

0.61

 BEGIN

0.60

<!--

0.59

end

0.59

 start

0.58

-->

0.58

 Begin

0.58

END

0.57

Activations Density 0.090%

HTML comment tags in the text

HTML or XML code sequences

HTML comments and DOCTYPE

No Comments

No Known Activations