INDEX

Explanations

questions and prompts related to privacy information and data collection practices

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

What is the m'th term

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

↵↵

-0.49

*/].

-0.45

 gerek

-0.45

 ficar

-0.45

 quede

-0.45

خار

-0.43

 pousse

-0.43

Földrajzportál

-0.43

 quedado

-0.42

 quedarse

-0.42

POSITIVE LOGITS

__":

0.73

новниш

0.73

IsContent

0.71

municipi

0.70

 CURIAM

0.68

__':

0.67

AccessorTable

0.66

 pinulongan

0.64

MigrationBuilder

0.64

Datuak

0.63

Activations Density 0.037%

questions and prompts related to privacy information and data collection practices

What is the m'th term

No Comments

No Known Activations