INDEX

Explanations

technical terms and keywords related to server configuration and API structure

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

={

-0.62

KindOfClass

-0.57

FECTION

-0.56

[];

-0.54

memset

-0.54

NumOf

-0.54

hofer

-0.53

>");

-0.53

aco

-0.52

`]

-0.52

POSITIVE LOGITS

Personendaten

0.78

DoubleQuotes

0.72

ChromeDriver

0.67

IBarButtonItem

0.65

writeFieldEnd

0.64

 string

0.62

 resourceCulture

0.62

 varchar

0.57

ArgsConstructor

0.57

writeField

0.57

Activations Density 0.322%

technical terms and keywords related to server configuration and API structure

No Comments

No Known Activations