INDEX

Explanations

numerical representations or statistics within the text

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

code/math notation

np_max-act-logits · gpt-4.1-mini-2025-04-14 Triggered by @arientigiacomo2003

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Duckworth

-0.88

 Bauer

-0.71

 Balfour

-0.69

 Ewing

-0.66

 Wainwright

-0.66

Dux

-0.65

 Schna

-0.64

Mauri

-0.64

 Lilli

-0.63

 Butterworth

-0.63

POSITIVE LOGITS

 Tuchel

0.70

 Dunkel

0.67

 Sweeney

0.67

 Loren

0.67

 ModelExpression

0.65

 Miro

0.64

 Davis

0.63

 Olms

0.62

 Biss

0.62

Davis

0.62

Activations Density 1.885%

numerical representations or statistics within the text

code/math notation

No Comments

No Known Activations