INDEX

Explanations

expressions of gratitude or thanks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

TypedDataSet

-0.70

 getGroup

-0.69

orum

-0.66

 nonatomic

-0.65

VM

-0.64

 Cage

-0.63

свое

-0.63

Persons

-0.62

MOL

-0.61

orkin

-0.60

POSITIVE LOGITS

 thanks

2.09

 Thanks

2.05

 THANKS

2.04

Thanks

2.01

thanks

1.99

THANKS

1.91

 graças

1.57

thx

1.57

 gracias

1.56

Thx

1.56

Activations Density 0.041%

expressions of gratitude or thanks

No Comments

No Known Activations