INDEX

Explanations

importance or significance in numerical values

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

Code-related words and abbreviations

np_acts-logits-general · gemini-2.0-flash

programming keywords

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

fjspx

-0.71

OGND

-0.70

orianCalendar

-0.68

 ویکی‌آمباردا

-0.63

帖最后由

-0.63

ɵɵ

-0.63

StructEnd

-0.60

ConstraintMaker

-0.59

Autoritní

-0.58

 useAppContext

-0.58

POSITIVE LOGITS

 Bucure

0.35

bý

0.35

expandindo

0.35

AppMethodBeat

0.33

 ExecuteAsync

0.32

0.31

noy

0.31

ø

0.31

ly

0.30

0.29

Activations Density 0.154%

importance or significance in numerical values

Code-related words and abbreviations

programming keywords

No Comments

No Known Activations