INDEX

Explanations

references to funding sources and support for research

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

grant numbers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 للمعارف

-0.88

 المعيارى

-0.67

ьаж

-0.66

 يتيمه

-0.65

 informée

-0.59

 AssemblyCompany

-0.58

ReusableCell

-0.58

 ProtoMessage

-0.58

webElementXpaths

-0.57

 <>",

-0.57

POSITIVE LOGITS

 table

0.39

 Academy

0.33

 drawing

0.32

end

0.32

 acting

0.31

 Table

0.31

 fons

0.31

 commercial

0.31

 liking

0.30

 form

0.30

Activations Density 0.071%

references to funding sources and support for research

grant numbers

No Comments

No Known Activations