INDEX

Explanations

technical terms related to software binding and requests

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

Code and file paths

np_acts-logits-general · gemini-2.0-flash

C# code and .NET framework

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 تضيفلها

-0.54

onOptions

-0.51

fare

-0.48

processable

-0.47

mapsto

-0.46

 desto

-0.46

__).

-0.45

wie

-0.45

 ImageIcon

-0.45

 scatt

-0.45

POSITIVE LOGITS

 '\\;'

0.67

 FishBase

0.61

 thyself

0.56

 ویکی‌آمباردا

0.54

 Wicidata

0.53

avyzd

0.52

abestanden

0.49

 nhàng

0.48

libft

0.47

zło

0.47

Activations Density 0.120%

technical terms related to software binding and requests

Code and file paths

C# code and .NET framework

No Comments

No Known Activations