INDEX

Explanations

phrases indicating positive emotional states or well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Normdatei

-0.65

 kasarigan

-0.65

Tikang

-0.65

 дописавши

-0.63

GEBURTSDATUM

-0.63

 '\\;'

-0.63

قایناق‌لار

-0.60

lccn

-0.59

occasione

-0.59

őle

-0.58

POSITIVE LOGITS

OK

2.32

ok

2.29

 okay

2.24

 alright

1.96

OK

1.90

okay

1.87

 fine

1.85

Ok

1.83

Ok

1.82

 OKAY

1.77

Activations Density 0.194%

phrases indicating positive emotional states or well-being

No Comments

No Known Activations