INDEX

Explanations

technical terms and function names related to programming and data manipulation

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

Tokens followed by parentheses or brackets

np_acts-logits-general · gemini-2.0-flash

parentheses and commas

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

 Centurion

-0.59

Hust

-0.55

SharedDtor

-0.54

 centrifug

-0.52

prefixer

-0.51

$[-

-0.51

 kasarigan

-0.51

 ✭✭

-0.50

Pru

-0.49

ρχ

-0.49

POSITIVE LOGITS

((

2.24

((

2.15

>((

1.83

,(

1.77

=(

1.71

:(

1.70

",(

1.70

',(

1.70

(((

1.68

)((

1.67

Activations Density 1.348%

technical terms and function names related to programming and data manipulation

Tokens followed by parentheses or brackets

parentheses and commas

No Comments

No Known Activations