INDEX

Explanations

references to visitors and imports in a coding or documentation context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 kasarigan

-0.77

ftagPool

-0.73

 تضيفلها

-0.72

########.

-0.72

 noDo

-0.71

errHandler

-0.71

RTLD

-0.69

mogat

-0.67

 ComVisible

-0.66

 onOptions

-0.64

POSITIVE LOGITS

存于互联网档案馆

0.62

PDF

0.59

={'

0.58

']")

0.56

'])

0.55

**/

0.54

"}

0.54

="\

0.53

TSI

0.53

LSA

0.52

Activations Density 0.064%

references to visitors and imports in a coding or documentation context

No Comments

No Known Activations