INDEX

Explanations

phrases expressing gratitude or appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 незавершена

-0.66

aarrggbb

-0.62

ebenarnya

-0.58

SpringBootTest

-0.57

 HasFactory

-0.57

ateľ

-0.56

 MonoBehaviour

-0.55

ComponentName

-0.55

antası

-0.55

OPHER

-0.55

POSITIVE LOGITS

 pleasure

2.18

pleasure

1.83

 honor

1.78

 privilege

1.74

 Pleasure

1.62

 honour

1.60

privilege

1.40

honor

1.39

 Honor

1.34

 HONOR

1.32

Activations Density 0.128%

phrases expressing gratitude or appreciation

No Comments

No Known Activations