INDEX

Explanations

technical specifications related to multimedia and connectivity features

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

Preceding function words or conjunctions

np_acts-logits-general · gemini-2.0-flash

built features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

بوابة

-0.79

ⓧ

-0.72

 BoxDecoration

-0.70

Referències

-0.68

RegressionTest

-0.65

 Observing

-0.64

ContentLoaded

-0.64

Diwedd

-0.63

Portail

-0.62

 onBind

-0.60

POSITIVE LOGITS

 built

0.82

Built

0.78

built

0.77

 Built

0.75

 Bluetooth

0.68

USB

0.63

 dual

0.62

 Dual

0.59

 powerful

0.59

Dual

0.58

Activations Density 0.169%

technical specifications related to multimedia and connectivity features

Preceding function words or conjunctions

built features

No Comments

No Known Activations