INDEX

Explanations

expressions and functions related to data manipulation and transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

rungsseite

-0.97

AndEndTag

-0.71

SequentialGroup

-0.69

RegressionTest

-0.68

GEBURTSDATUM

-0.67

ंदीखरीदारी

-0.65

DIPSETTING

-0.64

 المعيارى

-0.63

.*")]

-0.61

ApiModelProperty

-0.61

POSITIVE LOGITS

HasAnnotation

0.39

 lest

0.37

(!__

0.35

due

0.33

so

0.32

no

0.32

 afin

0.31

 مز

0.31

 εν

0.30

No

0.30

Activations Density 0.552%

expressions and functions related to data manipulation and transformation

No Comments

No Known Activations