INDEX

Explanations

prepositions that indicate locations or positions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Waray

-0.73

setVerticalGroup

-0.65

 >=",

-0.64

YMMV

-0.64

}>;

-0.63

"]));

-0.62

)))));

-0.59

"}")

-0.58

"];

-0.57

áu

-0.57

POSITIVE LOGITS

 dedans

0.67

 تانيه

0.60

Oke

0.57

Oke

0.56

mybatisplus

0.53

alui

0.53

 Crum

0.52

 środ

0.52

 desec

0.52

켰

0.50

Activations Density 0.247%

prepositions that indicate locations or positions

No Comments

No Known Activations