INDEX

Explanations

elements related to scientific concepts and discussions

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

Location or state of being

np_acts-logits-general · gemini-2.0-flash

being located or contained

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

 مشين

-0.88

MigrationBuilder

-0.69

IndentedString

-0.61

下载附件

-0.59

 ویکی‌پدیا

-0.58

awaiter

-0.56

 يتيمه

-0.54

fjspx

-0.54

 bezeichneter

-0.54

withIdentifier

-0.53

POSITIVE LOGITS

 located

1.76

 situated

1.47

 housed

1.46

 contained

1.40

 residing

1.36

located

1.33

 Located

1.31

Located

1.22

 embedded

1.19

 nestled

1.17

Activations Density 0.968%

elements related to scientific concepts and discussions

Location or state of being

being located or contained

No Comments

No Known Activations