INDEX

Explanations

components and elements in a graphical user interface or layout code

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

<start_of_turn>user

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

 berikutnya

-0.54

 pregunto

-0.52

 Widerspruch

-0.49

 musuh

-0.49

 conseguenze

-0.47

 Anfrage

-0.45

 perjuangan

-0.45

 Risiken

-0.44

 suaminya

-0.44

 Züge

-0.44

POSITIVE LOGITS

httphttps

0.64

ьаж

0.55

 resourceCulture

0.49

Personendaten

0.49

 Италијани

0.48

LookAnd

0.48

 surla

0.46

Filmographie

0.44

 ExecuteAsync

0.43

kháu

0.42

Activations Density 0.000%

components and elements in a graphical user interface or layout code

<start_of_turn>user

No Comments

No Known Activations

components and elements in a graphical user interface or layout code

<start_of_turn>user

No Comments

No Known Activations