INDEX

Explanations

words and references related to "Artron"

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

Token "Ar" followed by other tokens

np_acts-logits-general · gemini-2.0-flash

words starting with Ar

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

TagHelper

-0.70

 kasarigan

-0.69

PMailer

-0.63

Alike

-0.55

joueurs

-0.53

 propOrder

-0.52

клопе

-0.51

 مواليد

-0.51

__":

-0.51

saraba

-0.50

POSITIVE LOGITS

tvguidetime

0.54

 ActiveRecord

0.51

 juries

0.45

 ktorí

0.45

Kaieteur

0.45

WireFormat

0.45

Portale

0.44

 Argo

0.42

 ImageIcon

0.41

erialization

0.41

Activations Density 0.103%

words and references related to "Artron"

Token "Ar" followed by other tokens

words starting with Ar

No Comments

No Known Activations