INDEX

Explanations

structures and functions related to data or information processing in programming or computing contexts

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

Code or mathematical notation

np_acts-logits-general · gemini-2.0-flash

technical adjectives and programming terms

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 للمعارف

-0.74

 ComVisible

-0.67

providedIn

-0.65

 OFDb

-0.65

 FetchType

-0.65

Autoritní

-0.65

 فريبيس

-0.64

 ErrIntOverflow

-0.60

Sucesor

-0.58

 الرياضيه

-0.57

POSITIVE LOGITS

RegistryLite

0.73

BeginContext

0.68

makeConstraints

0.67

Referencies

0.59

ConstraintMaker

0.56

 dieß

0.56

SharedCtor

0.55

存于互联网档案馆

0.54

Personendaten

0.53

 initComponents

0.52

Activations Density 2.355%

structures and functions related to data or information processing in programming or computing contexts

Code or mathematical notation

technical adjectives and programming terms

No Comments

No Known Activations