INDEX

Explanations

occurrences of the letter 'a' in various contexts

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

vig

-0.78

 investi

-0.75

 compri

-0.72

 impact

-0.72

 kari

-0.70

 vider

-0.68

men

-0.68

ven

-0.67

ves

-0.67

 opis

-0.67

POSITIVE LOGITS

1.25

getA

1.25

1.06

 brancas

1.01

aA

1.01

QApplication

0.99

dA

0.89

 vermelhas

0.89

 ansatte

0.88

OA

0.86

Activations Density 0.395%

occurrences of the letter 'a' in various contexts

No Comments

No Known Activations