INDEX

Explanations

usage of the preposition "на" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Roskov

-0.53

vœ

-0.51

cartItem

-0.50

 Italij

-0.47

 contemporain

-0.47

 ennemi

-0.46

 Polsek

-0.45

 bolsillos

-0.44

 AttributeSet

-0.44

 يتيمه

-0.44

POSITIVE LOGITS

 на

1.16

auf

1.10

na

0.96

på

0.87

На

0.83

Na

0.81

 На

0.80

 aufs

0.74

Auf

0.72

Auf

0.71

Activations Density 0.079%

usage of the preposition "на" in various contexts

No Comments

No Known Activations