INDEX

Explanations

identifiers and keywords related to programming or data structures

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

with capitalized initial letters

np_acts-logits-general · gemini-2.0-flash

universal cosmic

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

 vérit

-0.78

 hâte

-0.74

 vermelhas

-0.65

 dieux

-0.65

 engraçadas

-0.64

 bonté

-0.64

 lèvres

-0.64

 florales

-0.63

 espirituales

-0.63

 journaux

-0.62

POSITIVE LOGITS

DE

0.76

MU

0.72

NA

0.72

LA

0.71

DI

0.71

 multer

0.69

FA

0.67

AJ

0.67

VI

0.67

MI

0.66

Activations Density 0.066%

identifiers and keywords related to programming or data structures

with capitalized initial letters

universal cosmic

No Comments

No Known Activations