INDEX

Explanations

phrases or references related to notable individuals, specifically in legal or influential contexts

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

Followed by numbers or special characters

np_acts-logits-general · gemini-2.0-flash

citation suffixes (e.g., P.3d)

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agaimana

-0.64

MigrationBuilder

-0.64

NameInMap

-0.63

AddressBook

-0.62

kku

-0.60

 ويكيميديا

-0.60

 import

-0.59

 CanadaChoose

-0.58

 виправивши

-0.57

oto

-0.57

POSITIVE LOGITS

 للاسماء

0.63

findpost

0.60

 Communists

0.54

 känd

0.52

 světa

0.52

__":

0.52

 knuckles

0.51

 Pingback

0.50

ettbewer

0.50

 صوتيه

0.49

Activations Density 0.023%

phrases or references related to notable individuals, specifically in legal or influential contexts

Followed by numbers or special characters

citation suffixes (e.g., P.3d)

No Comments

No Known Activations