INDEX

Explanations

patterns of legal terminology and judicial processes

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

Numbers followed by punctuation

np_acts-logits-general · gemini-2.0-flash

numbered list items

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

клопе

-0.57

hol

-0.57

DaoImpl

-0.51

HideFlags

-0.49

andaag

-0.48

 look

-0.48

fieras

-0.46

σουμε

-0.46

holder

-0.46

ngdoc

-0.45

POSITIVE LOGITS

ValueStyle

0.64

IndentedString

0.57

脚注の使い方

0.53

:✨

0.53

Autoritní

0.52

 autorytatywna

0.52

Personensuche

0.52

InitVars

0.51

 ComVisible

0.51

 متعلقه

0.50

Activations Density 0.107%

patterns of legal terminology and judicial processes

Numbers followed by punctuation

numbered list items

No Comments

No Known Activations