INDEX

Explanations

content related to block formatting or structure in programming or coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 doInBackground

-0.88

 propOrder

-0.86

IntoConstraints

-0.78

 CURIAM

-0.78

GraphicsUnit

-0.76

providedIn

-0.75

ंदीखरीदारी

-0.72

 viewDidLoad

-0.71

اریخ

-0.70



-0.68

POSITIVE LOGITS

iesz

0.50

undang

0.49

धी

0.48

िख

0.48

 незавершена

0.48

 biosynthesis

0.46

InjectAttribute

0.45

ApiResponse

0.45

vra

0.45

 Lombardi

0.45

Activations Density 0.182%

content related to block formatting or structure in programming or coding contexts

No Comments

No Known Activations