INDEX

Explanations

terms related to online services and products

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

nureflex, assignment help, proxy, shoes

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

 pungkasnya

-0.45

LookAnd

-0.43

queryInterface

-0.43

RTHOOK

-0.39

 ویکی‌پدی

-0.39

الحياه

-0.37

nerie

-0.35

 endblock

-0.35

UserScript

-0.35

 مشين

-0.34

POSITIVE LOGITS

%)$

0.49

intios

0.49

straints

0.47

 HDPE

0.46

 HasFactory

0.46

 Manganese

0.46

FirebaseUser

0.46

<>();

0.44

 NIST

0.44

 🤣

0.44

Activations Density 0.008%

terms related to online services and products

nureflex, assignment help, proxy, shoes

No Comments

No Known Activations