INDEX

Explanations

negative signs or indicators in numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 فريبيس

-0.79

 noDo

-0.78

?";

-0.75

PostInfinity

-0.73

ſehen

-0.71

NameInMap

-0.69

()")

-0.69

fjspx

-0.68

 Италијани

-0.68

 ویکی‌پدی

-0.68

POSITIVE LOGITS

,-

1.48

:-

1.05

,,

0.77

,--

0.76

:-

0.75

,-.

0.75

,–

0.70

;-

0.69

,.

0.66

,-,

0.65

Activations Density 0.249%

negative signs or indicators in numerical data

No Comments

No Known Activations