INDEX

Explanations

mathematical symbols and notations relevant to equations and scientific formulas

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

subsequent transport into cells

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

HasIndex

-0.50

OGND

-0.46

contentLoaded

-0.41

WithMany

-0.40

 trasc

-0.38

挑

-0.38

FunctionFlags

-0.38

 nakalista

-0.37

pinch

-0.37

 createState

-0.37

POSITIVE LOGITS

 przeznac

0.48

ClientRect

0.46

oa̍t

0.42

 eventually

0.41

 destinations

0.40

 useNavigate

0.40

 akár

0.39

Andere

0.38

MLLoader

0.38

 jiné

0.38

Activations Density 0.102%

mathematical symbols and notations relevant to equations and scientific formulas

subsequent transport into cells

No Comments

No Known Activations