INDEX

Explanations

keywords and classes associated with programming modules and components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

oa̍t

-0.63

 ویکی‌پدی

-0.61

älde

-0.60

 ivelany

-0.59

RefNanny

-0.58

AsUp

-0.58

**

-0.56

ண்டும்

-0.53

}))

-0.52

 ".";

-0.52

POSITIVE LOGITS

ScopeManager

0.72

+#+

0.64

SupportActionBar

0.59

 NSCoder

0.56

DockStyle

0.56

 createSlice

0.55

 práctico

0.55

__*/

0.55

WebServlet

0.53

Parcelize

0.52

Activations Density 0.302%

keywords and classes associated with programming modules and components

No Comments

No Known Activations