INDEX

Explanations

quantified measures and statistical data related to experimental results

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

Mathematical/scientific notation with symbols

np_acts-logits-general · gemini-2.0-flash

± with numbers or conditions

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

-0.56

-0.53

<strong>

-0.52

<eos>

-0.51

...

-0.51

-0.50

-0.49

...

-0.49

POSITIVE LOGITS

出版年

0.97

 فريبيس

0.83

 propOrder

0.80

 препратки

0.79

 الحره

0.78

GenerationType

0.77

 ―――――

0.75

 myſelf

0.75

 Waray

0.74

 Anſ

0.74

Activations Density 0.733%

quantified measures and statistical data related to experimental results

Mathematical/scientific notation with symbols

± with numbers or conditions

No Comments

No Known Activations