INDEX

Explanations

categories related to various topics or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

EndContext

-0.67

GridColumn

-0.58

möbel

-0.55

 ويكيميديا

-0.54

.*")]

-0.54

AsUp

-0.53

addContainerGap

-0.53

 goederen

-0.52

تقاوى

-0.52

ьаж

-0.52

POSITIVE LOGITS

 صوتيه

0.57

AlterField

0.57

findpost

0.51

igerung

0.49

 يتيمه

0.48

ByUrl

0.47

racuse

0.47

 للمعارف

0.46

SourceChecksum

0.45

Jeografia

0.45

Activations Density 0.027%

categories related to various topics or classifications

No Comments

No Known Activations