INDEX

Explanations

scientific terms related to measurements and observations

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

prime factors or numbers

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

 CanadaChoose

-0.47

ViewFeatures

-0.44

клопе

-0.44

 SEPAR

-0.44

 يتيمه

-0.43

 للمعارف

-0.43

ErrUnexpectedEOF

-0.42

 separ

-0.41

encodeWith

-0.41

TestBed

-0.40

POSITIVE LOGITS

 insuffisamment

0.52

GOTREF

0.42

Спољашње

0.41

 InputDecoration

0.40

存于互联网档案馆

0.39

 NSCoder

0.37

octanol

0.36

Примітки

0.35

页面存档备份

0.35

 OMITBAD

0.34

Activations Density 0.122%

scientific terms related to measurements and observations

prime factors or numbers

No Comments

No Known Activations