INDEX

Explanations

punctuation marks and their usage

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

after <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

 createSprite

-0.50

 defire

-0.50

 AppCompatTheme

-0.49

viewDidLoad

-0.49

ToRefresh

-0.48

AsUp

-0.48

 ब्रेकडाउन

-0.48

EnableWeb

-0.47

 chofe

-0.47

enderror

-0.47

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.67

GOTREF

0.47

 Numerade

0.44

 للاسماء

0.44

 chi̍t

0.43

CppCodeGen

0.42

 AssemblyCompany

0.42

Encyklopedia

0.40

 OMITBAD

0.40

 الحره

0.39

Activations Density 0.000%

punctuation marks and their usage

after <start_of_turn>user

No Comments

No Known Activations