INDEX

Explanations

geographical and administrative terms related to locations and divisions

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

administrative divisions and roles

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

NoSuchAlgorithm

-0.46

الحياه

-0.43

 ideen

-0.40

ContentAsync

-0.39

Портали

-0.39

 cowards

-0.38

ſy

-0.37

 coward

-0.37

CompleteListener

-0.36

IntoConstraints

-0.36

POSITIVE LOGITS

StoryboardSegue

0.45

enterOuterAlt

0.44

省市镇

0.43

dafx

0.43

tinyos

0.42

Tracce

0.42

libft

0.41

pieler

0.39

InjectMocks

0.38

marshaller

0.38

Activations Density 0.003%

geographical and administrative terms related to locations and divisions

administrative divisions and roles

No Comments

No Known Activations