INDEX

Explanations

phrases related to games and gameplay

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

card usage in player functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

transQ

-0.48

KURZBESCHREIBUNG

-0.46

 rodeo

-0.46

intios

-0.45

 Rodeo

-0.45

 LCCN

-0.45

ValueGenerated

-0.43

 pageant

-0.42

JTextArea

-0.42

 EconPapers

-0.41

POSITIVE LOGITS

انيف

0.46

sprogramm

0.43

UnusedPrivate

0.43

 segíts

0.41

StoryboardSegue

0.40

 BoxFit

0.40

 telefonu

0.40

 kağıt

0.39

 gutem

0.39

 dAtA

0.39

Activations Density 0.009%

phrases related to games and gameplay

card usage in player functions

No Comments

No Known Activations