INDEX

Explanations

proper nouns and names in various contexts

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

Appears after specific abbreviations or acronyms

np_acts-logits-general · gemini-2.0-flash

complementary, MARK KORVAYAN, Spelterini, core vitrectomy, Skill Kyutama

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

PerformLayout

-0.79

expandindo

-0.69

 AssemblyTitle

-0.63

routeProvider

-0.62

DetailComponent

-0.61

queryInterface

-0.61

LookAnd

-0.58

 صوتيه

-0.57

Tuc

-0.57

styleUrls

-0.55

POSITIVE LOGITS

bootstrapcdn

0.66

Хьажоргаш

0.59

IMDG

0.56

TagMode

0.52

cyklopedia

0.48

Distribuzione

0.48

IEEE

0.47

irão

0.45

znego

0.45

ectl

0.44

Activations Density 0.294%

proper nouns and names in various contexts

Appears after specific abbreviations or acronyms

complementary, MARK KORVAYAN, Spelterini, core vitrectomy, Skill Kyutama

No Comments

No Known Activations