INDEX

Explanations

technical terms and annotations related to object-relational mapping (ORM) in programming

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

programming code and data serialization

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

 autorytatywna

-0.41

 najbolj

-0.35

Seriously

-0.33

Personendaten

-0.33

EDEFAULT

-0.33

ValueGenerated

-0.32

parsedMessage

-0.31

kloped

-0.31

@"/

-0.31

Fordítás

-0.29

POSITIVE LOGITS

LookAnd

0.59

 kasarigan

0.57

 Waray

0.51

دانشنامهٔ

0.50

BeginInit

0.49

 Audiodateien

0.48

发表于

0.48

⟬

0.47

tonode

0.47

VYMaps

0.46

Activations Density 0.011%

technical terms and annotations related to object-relational mapping (ORM) in programming

programming code and data serialization

No Comments

No Known Activations