INDEX

Explanations

expressions indicating frequency or rate per unit of measurement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

>>;

-0.61

 esto

-0.61

ırken

-0.53

<!--

-0.51

 CHtml

-0.51

følgelig

-0.50

jadi

-0.50

yii

-0.49

 Timur

-0.49

esto

-0.49

POSITIVE LOGITS

per

1.02

Chaque

0.94

EACH

0.91

 each

0.89

 mỗi

0.86

 every

0.86

 chaque

0.86

 EACH

0.84

every

0.84

each

0.79

Activations Density 0.112%

expressions indicating frequency or rate per unit of measurement

No Comments

No Known Activations