INDEX

Explanations

elements of a structured data format or programming code

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

Tokens preceding URLs or code snippets

np_acts-logits-general · gemini-2.0-flash

HTML links with relative paths

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

 Oppen

-0.71

 Henderson

-0.70

 AssemblyCulture

-0.70

 Preston

-0.70

Preston

-0.68

RDA

-0.68

AndEndTag

-0.65

 Alembic

-0.63

 Clayton

-0.63

 Kendra

-0.62

POSITIVE LOGITS

 Wyman

0.70

 Rasmus

0.67

 مرئيه

0.63

 Kazan

0.62

 Rodriguez

0.59

 Luciano

0.59

 Hartman

0.59

 Srivastava

0.58

 Marlowe

0.58

 Darryl

0.58

Activations Density 0.562%

elements of a structured data format or programming code

Tokens preceding URLs or code snippets

HTML links with relative paths

No Comments

No Known Activations