INDEX

Explanations

instances of the word "に" which indicates relationships or connections

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inė

-0.54

Utils

-0.51

 alrededores

-0.51

nová

-0.51

 habet

-0.50

 quæ

-0.50

igheid

-0.50

 linkovi

-0.49

なが

-0.48

 scolaire

-0.48

POSITIVE LOGITS

기에

0.80

)";

0.74

acağına

0.71

])):

0.69

 onPostExecute

0.69

mybatisplus

0.69

feinander

0.69

SequentialGroup

0.68

"]').

0.67

்கு

0.67

Activations Density 0.044%

instances of the word "に" which indicates relationships or connections

No Comments

No Known Activations