INDEX

Explanations

questions and expressions of curiosity in various languages

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

Followed by questions in different languages

np_acts-logits-general · gemini-2.0-flash

quelqu'un or asking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.72

ArrowToggle

-0.69

setVerticalGroup

-0.67

libft

-0.62

})));

-0.62

 noqa

-0.61

titleMargin

-0.59

 "..\..\

-0.59

 متعلقه

-0.58

ViewFeatures

-0.56

POSITIVE LOGITS

colhead

0.56

Redaktion

0.56

 FormGroup

0.55

ButterKnife

0.54

spreis

0.52

principalColumn

0.52

zegor

0.52

存于互联网档案馆

0.50

 typeof

0.49

sprogramm

0.49

Activations Density 0.061%

questions and expressions of curiosity in various languages

Followed by questions in different languages

quelqu'un or asking

No Comments

No Known Activations