INDEX

Explanations

references to future work and outcomes in academic writing

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

states or conditions concluding

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

+#+#

-0.67

出版年

-0.66

المناصب

-0.60

Personendaten

-0.59

الحياه

-0.56

 ویکی‌پدیا

-0.52

 يتيمه

-0.52

 समीक्षाओं

-0.50

Бахар

-0.48

Tikang

-0.48

POSITIVE LOGITS

ViewFeatures

0.42

GOTREF

0.42

 кстати

0.41

 AssemblyCompany

0.40

LookAnd

0.40

 also

0.40

also

0.39

thenReturn

0.38

 however

0.38

 similarly

0.36

Activations Density 0.063%

references to future work and outcomes in academic writing

states or conditions concluding

No Comments

No Known Activations