INDEX

Explanations

references to visual elements, particularly images and their associated titles or covers

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

click on image above

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

StoreMessageInfo

-0.49

GraphicsUnit

-0.44

MethodManager

-0.39

ExtendWith

-0.38

SBATCH

-0.38

 Shore

-0.38

//}

-0.36

stylers

-0.34

currentColor

-0.33

WebServlet

-0.33

POSITIVE LOGITS

 defaultstate

0.55

 незавершена

0.52

rinth

0.49

\{\\

0.49

ngths

0.48

፩

0.48

 saites

0.45

CloseOperation

0.44

 linkovi

0.44

 ApiClient

0.43

Activations Density 0.019%

references to visual elements, particularly images and their associated titles or covers

click on image above

No Comments

No Known Activations