INDEX

Explanations

terms related to health, wellness, and intervention strategies

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

followed by commas

np_acts-logits-general · gemini-2.0-flash

counts and country names

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

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.75

queryInterface

-0.61

InjectAttribute

-0.57

 PagesJaunes

-0.56

enumii

-0.56

Spoljašnje

-0.53

SPJ

-0.51

 MainAxisSize

-0.51

 Pingback

-0.51

__':

-0.51

POSITIVE LOGITS

Xna

0.39

 juridiques

0.33

 kapturem

0.33

IEDAD

0.32

 inconnu

0.32

Viited

0.31

 nonUne

0.30

0.29

Rhestr

0.28

AdapterView

0.28

Activations Density 0.949%

terms related to health, wellness, and intervention strategies

followed by commas

counts and country names

No Comments

No Known Activations