INDEX

Explanations

punctuation marks and formatting symbols used in code or structured data

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DrawerToggle

-0.53

 ویکی‌پدی

-0.49

 ब्रेकडाउन

-0.49

SequentialGroup

-0.47

存于互联网档案馆

-0.44

abases

-0.42

DECREF

-0.41

annica

-0.41

 NUKAT

-0.40

POSITIVE LOGITS

Hauptartikel

0.46

Fordítás

0.45

 PhpStorm

0.43

ientôt

0.42

 Pingback

0.40

المكان

0.40

didSet

0.38

 soal

0.38

Wymiary

0.38

 stake

0.37

Activations Density 0.336%

punctuation marks and formatting symbols used in code or structured data

No Comments

No Known Activations