INDEX

Explanations

statistical terms and phrases pertaining to data analysis and interpretation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DebuggerStep

-0.73

ItemBackground

-0.67

nasium

-0.67

AndEndTag

-0.65

下载附件

-0.64

 ―――――

-0.64

 GoogleFonts

-0.63

 itſelf

-0.62

 AssemblyCompany

-0.62

]--;

-0.62

POSITIVE LOGITS

 المعيارى

0.76

didSet

0.57

LookAnd

0.52

AsUp

0.51

Ligações

0.49

0.46

 kasarigan

0.45

Legături

0.44

 kepad

0.43

 doInBackground

0.43

Activations Density 0.717%

statistical terms and phrases pertaining to data analysis and interpretation

No Comments

No Known Activations