INDEX

Explanations

variables and their relationships in mathematical or scientific contexts

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

Mathematical or scientific notation

np_acts-logits-general · gemini-2.0-flash

mathematical Greek letters and superscripts

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

 Kahn

-0.69

PSR

-0.61

 McDonough

-0.59

Kog

-0.57

 Marra

-0.57

 McNamara

-0.56

 Bryan

-0.54

skat

-0.54

 Khat

-0.53

 McDowell

-0.52

POSITIVE LOGITS

 Cord

0.89

 CORD

0.81

 Joyce

0.76

 Pang

0.75

 Cort

0.74

 Vella

0.74

Cord

0.74

 MART

0.73

CORD

0.73

 Mart

0.72

Activations Density 0.635%

variables and their relationships in mathematical or scientific contexts

Mathematical or scientific notation

mathematical Greek letters and superscripts

No Comments

No Known Activations