INDEX

Explanations

references to support and services provided by businesses

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

our customers and business

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

SequentialGroup

-0.47

хьтан

-0.46

toHaveBeen

-0.43

ValueStyle

-0.41

oneofs

-0.40

RTLR

-0.40

 ویکی‌آمباردا

-0.40

 bucal

-0.40

 MethodInfo

-0.39

 tumour

-0.39

POSITIVE LOGITS

DoubleQuotes

0.50

 astore

0.41

tangentMode

0.40

 мәгълү

0.39

 company

0.39

centralwidget

0.39

SpringRunner

0.38

TestingModule

0.38

UpInside

0.37

quartered

0.36

Activations Density 0.021%

references to support and services provided by businesses

our customers and business

No Comments

No Known Activations