INDEX

Explanations

details regarding experimental design and methodology in research studies

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

"Per" or "each" followed by a unit or category

np_acts-logits-general · gemini-2.0-flash

items per group

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

ValueStyle

-0.75

 विश्वसनीयता

-0.66

Xna

-0.65

StackNavigator

-0.63

 <=",

-0.62

awakeFromNib

-0.61

ThemeOverlay

-0.58

 للمعارف

-0.58

 -->>

-0.56

 intStringLen

-0.54

POSITIVE LOGITS

 each

3.65

each

3.05

Each

2.91

 Each

2.86

 EACH

2.59

EACH

2.39

 chaque

2.33

 chacun

2.21

 chacune

2.16

 fiecare

2.14

Activations Density 1.178%

details regarding experimental design and methodology in research studies

"Per" or "each" followed by a unit or category

items per group

No Comments

No Known Activations