INDEX

Explanations

programming and technical terms related to data structures or algorithms

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

or abbreviations directly followed by other capitalized words

np_acts-logits-general · gemini-2.0-flash

abbreviations and acronyms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Вікі

-0.49

tagext

-0.44

 Duggan

-0.44

 Bologna

-0.42

richTextPanel

-0.42

 AudioClip

-0.41

 Hahn

-0.41

ombie

-0.41

govina

-0.40

 Matta

-0.40

POSITIVE LOGITS

DS

0.92

FS

0.90

TSS

0.89

TS

0.89

LS

0.88

GS

0.87

HS

0.87

RS

0.87

OSS

0.86

QS

0.85

Activations Density 2.039%

programming and technical terms related to data structures or algorithms

or abbreviations directly followed by other capitalized words

abbreviations and acronyms

No Comments

No Known Activations