INDEX

Explanations

content related to Facebook and social media interactions

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

"Facebook" or related terms

np_acts-logits-general · gemini-2.0-flash

Facebook pages and developers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Personendaten

-0.84

AndroidJUnit

-0.56

 Peck

-0.52

 Clippers

-0.51

HasIndex

-0.51

 NSCoder

-0.50

 Duckworth

-0.50

Scénario

-0.50

mij

-0.48

 Hartman

-0.48

POSITIVE LOGITS

 Facebook

1.97

Facebook

1.80

 facebook

1.75

facebook

1.72

FB

1.68

 FACEBOOK

1.61

Fb

1.58

fb

1.55

FACEBOOK

1.46

FB

1.43

Activations Density 0.106%

content related to Facebook and social media interactions

"Facebook" or related terms

Facebook pages and developers

No Comments

No Known Activations