INDEX

Explanations

keywords related to API and request functionalities in programming code

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

Code syntax, methods, and API requests

np_acts-logits-general · gemini-2.0-flash

potentially pathogenic

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

цездатний

-0.54

ísima

-0.53

UpInside

-0.51

 doInBackground

-0.51

WritableDatabase

-0.51

corrência

-0.50

einander

-0.49

featureID

-0.48

ouin

-0.48

 Wund

-0.47

POSITIVE LOGITS

expandindo

1.11

OGND

0.62

Général

0.56

 Affiliations

0.55

SourceChecksum

0.54

 برانيه

0.52

 jár

0.51

ंदीखरीदारी

0.50

Hauptartikel

0.49

GEBURTSDATUM

0.49

Activations Density 0.079%

keywords related to API and request functionalities in programming code

Code syntax, methods, and API requests

potentially pathogenic

No Comments

No Known Activations