INDEX

Explanations

patterns of high activity, indicating strong engagement or interest in a topic

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

question/answer format

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

 للمعارف

-0.55

ValueStyle

-0.51

Hochspringen

-0.44

 Réponses

-0.44

addContainerGap

-0.44

 aapt

-0.43

 zugesch

-0.41

WebServlet

-0.40

 useAppContext

-0.39

 صوتيه

-0.39

POSITIVE LOGITS

OGND

0.52

 propOrder

0.43

SharedDtor

0.43

bcryptjs

0.42

MigrationBuilder

0.40

 saurait

0.40

CloseOperation

0.39

Autoritní

0.38

 inoxidable

0.36

Дереккөздер

0.36

Activations Density 0.000%

patterns of high activity, indicating strong engagement or interest in a topic

question/answer format

No Comments

No Known Activations