INDEX

Explanations

quantitative measurements and statistical analyses related to health and nutrition

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Numbers or values

np_acts-logits-general · gemini-2.0-flash

values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 ब्रेकडाउन

-0.78

AndEndTag

-0.73

 ویکی‌آمباردا

-0.72

 tartalomajánló

-0.71

ScopeManager

-0.65

__":

-0.64

thâu

-0.63

 Италијани

-0.62

__':

-0.61

ACHUSET

-0.59

POSITIVE LOGITS

 Goldstein

0.35

 Varies

0.35

 Insel

0.35

bukaan

0.35

 обычно

0.34

 montanha

0.33

Generally

0.33

Usually

0.33

 adecuados

0.32

 soins

0.32

Activations Density 0.681%

quantitative measurements and statistical analyses related to health and nutrition

Numbers or values

values and measurements

No Known Activations