INDEX

Explanations

references to the verb "am" or its variations, indicating states of being or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

openConnection

-0.74

 peric

-0.71

inca

-0.68

GTC

-0.66

 Clayton

-0.63

 Bole

-0.62

WithIOException

-0.62

aux

-0.62

ICAS

-0.61

 Frazer

-0.61

POSITIVE LOGITS

am

1.54

Am

1.32

Am

1.17

AM

0.96

Iam

0.94

Ami

0.92

am

0.85

Ami

0.83

 Amman

0.83

are

0.81

Activations Density 0.074%

references to the verb "am" or its variations, indicating states of being or existence

No Comments

No Known Activations