INDEX

Explanations

programming terminology related to dynamic data handling and manipulation

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

Code or markup generation

np_acts-logits-general · gemini-2.0-flash

dynamic or programmatically

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

 betweenstory

-0.65

 AssemblyProduct

-0.63

GraphicsUnit

-0.62

iettivo

-0.61

ParallelGroup

-0.58

 kasarigan

-0.57

keyColumn

-0.57

DIPSETTING

-0.56

SequentialGroup

-0.55

ंदीखरीदारी

-0.55

POSITIVE LOGITS

č

0.29

exitRule

0.29

 نق

0.29

res

0.28

di

0.27

 spalle

0.26

diğim

0.26

Whe

0.26

đ

0.26

 tail

0.25

Activations Density 3.136%

programming terminology related to dynamic data handling and manipulation

Code or markup generation

dynamic or programmatically

No Comments

No Known Activations