INDEX

Explanations

references to institutions, companies, or organizations

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

 Мексичка

-0.81

-0.74

存于互联网档案馆

-0.72

Rhestr

-0.71

Autoritní

-0.70

 مرئيه

-0.69

########.

-0.69

出版年

-0.67

 <=",

-0.66

 فريبيس

-0.66

POSITIVE LOGITS

 project

0.48

álja

0.47

IntentFilter

0.47

 agency

0.45

 Existenz

0.43

 unit

0.43

 organization

0.43

 MonoBehaviour

0.43

 voyez

0.42

act

0.41

Activations Density 0.227%

references to institutions, companies, or organizations

No Comments

No Known Activations