INDEX

Explanations

occurrences of whitespace or formatting characters in code

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

programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

Hentet

-0.50

 صوتيه

-0.50

Autoritní

-0.50

Personendaten

-0.49

 Мексичка

-0.47

 AssemblyTitle

-0.46

 betweenstory

-0.43

rmdir

-0.41

Viitteet

-0.41

ViewImports

-0.40

POSITIVE LOGITS

beforeEach

0.61

ɵ

0.41

BeforeEach

0.41

fak

0.40

adpleegd

0.39

webElementGuid

0.38

garmin

0.36

setupUi

0.36

BeforeClass

0.36

 Prefix

0.36

Activations Density 0.001%

occurrences of whitespace or formatting characters in code

programming contexts

No Comments

No Known Activations

occurrences of whitespace or formatting characters in code

programming contexts

No Comments

No Known Activations