INDEX

Explanations

class definitions in programming 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

 betweenstory

-0.66

 EconPapers

-0.64

endregion

-0.52

airobi

-0.50

netbeans

-0.49

 jsonify

-0.46

PackageManager

-0.45

phosa

-0.45

 isNameExpr

-0.44

 Mali

-0.44

POSITIVE LOGITS

SourceChecksum

0.59

 Comprometido

0.52

 ویکی‌پدی

0.51

class

0.50

 مشارکت‌کنندگان

0.48

 živ

0.47

expandindo

0.45

 ویکی‌پدیا

0.43

最快更新

0.43

ningss

0.42

Activations Density 0.000%

class definitions in programming code

<start_of_turn>user

No Comments

No Known Activations