INDEX

Explanations

HTML tags and attributes related to navigation and layout structures

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

Followed by HTML image tag attributes

np_acts-logits-general · gemini-2.0-flash

"><

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

 horseshoe

-0.62

니다

-0.60

mybatisplus

-0.56

.*")]

-0.54

发表于

-0.53

\]

-0.50

 Salim

-0.50

EntityFramework

-0.50

Autoritní

-0.50

 Conservancy

-0.49

POSITIVE LOGITS

"><

1.50

><

1.45

'><

1.35

;"><

1.21

."<

1.20

'<

1.15

;<

1.15

:<

1.14

]<

1.13

"<

1.12

Activations Density 0.114%

HTML tags and attributes related to navigation and layout structures

Followed by HTML image tag attributes

"><

No Comments

No Known Activations