INDEX

Explanations

references to golf-related terminology and scoring rules

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

first pass

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

ErrorListener

-0.64

 ویکی‌پدیای

-0.64

CloseOperation

-0.58

/**

-0.57

Oneof

-0.57

IsMutable

-0.56

 rounds

-0.54

//

-0.54

 getItemCount

-0.53

makeConstraints

-0.52

POSITIVE LOGITS

 fair

0.59

 green

0.58

Risk

0.55

par

0.55

 Risk

0.54

 kaarangay

0.54

 Biar

0.54

 risk

0.54

 carry

0.53

 Fair

0.53

Activations Density 0.092%

references to golf-related terminology and scoring rules

followed by prepositions

first pass

No Comments

No Known Activations