INDEX

Explanations

document delimiters and markers related to structure or formatting

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

Tokens after a capitalized word

np_acts-logits-general · gemini-2.0-flash

immediate children; neighborhoods

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

])));

-0.68

eqn

-0.55

 CreateTagHelper

-0.53

")));

-0.52

 &___

-0.52

loroethene

-0.52

bitField

-0.51

"]));

-0.51

))));

-0.51

:✨

-0.50

POSITIVE LOGITS

 itſelf

0.82

 RSSSF

0.77

 NDEBUG

0.70

脚注の使い方

0.68

 BeautifulSoup

0.67

 Schengen

0.67

 Cæsar

0.66

 wikipagina

0.66

 crdi

0.66

 ſche

0.65

Activations Density 0.609%

document delimiters and markers related to structure or formatting

Tokens after a capitalized word

immediate children; neighborhoods

No Comments

No Known Activations