INDEX

Explanations

mathematical notation and structures

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

Tokens preceding parentheses and brackets

np_acts-logits-general · gemini-2.0-flash

Swift storage properties

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

 Norwood

-0.78

 Corbett

-0.69

 Hyman

-0.68

 Aure

-0.66

 Holliday

-0.64

LTD

-0.64

 Corsica

-0.64

 Shand

-0.61

gator

-0.61

 Slade

-0.61

POSITIVE LOGITS

 McConnell

0.80

 Pohl

0.75

Guil

0.71

 Guil

0.67

 незавершена

0.66

 Cheshire

0.66

Oke

0.60

 brazil

0.59

 Amelia

0.59

 Guilford

0.58

Activations Density 1.407%

mathematical notation and structures

Tokens preceding parentheses and brackets

Swift storage properties

No Comments

No Known Activations