INDEX

Explanations

mathematical constants and expressions, particularly related to pi

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 tung

-0.67

 Jennings

-0.61

nder

-0.60

ah

-0.58

Lester

-0.58

 KENN

-0.56

</strong>

-0.56

force

-0.55

oog

-0.54

 protoimpl

-0.53

POSITIVE LOGITS

pi

1.41

pi

1.38

PI

1.23

Pi

1.21

π

1.19

 Pierson

1.16

π

1.16

 pips

1.11

PI

1.11

 radians

1.09

Activations Density 0.156%

mathematical constants and expressions, particularly related to pi

No Comments

No Known Activations