INDEX

Explanations

phrases emphasizing the concept of "all" or totality in various contexts

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

"all"

np_acts-logits-general · gemini-2.0-flash

all followed by determiner or of

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.93

 VIAF

-0.79

})).

-0.76

IndentedString

-0.73

 Moskva

-0.72

InjectAttribute

-0.71

})),

-0.68

Tikang

-0.67

}`).

-0.67

 Spinoza

-0.67

POSITIVE LOGITS

 sorts

1.05

 kinds

0.98

 mọi

0.78

llllllll

0.77

All

0.74

 demás

0.74

 deleteAll

0.74

ReadAll

0.72

ALL

0.71

All

0.69

Activations Density 0.207%

phrases emphasizing the concept of "all" or totality in various contexts

"all"

all followed by determiner or of

No Comments

No Known Activations