INDEX

Explanations

references to dining or eating experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

!*\

-0.62

selaer

-0.57

\}\\

-0.54

tenberg

-0.53

ITUTE

-0.53

achable

-0.53

ollectionView

-0.52

allo

-0.50

StructEnd

-0.50

 Representative

-0.49

POSITIVE LOGITS

 dining

2.66

 Dining

2.45

dining

2.36

Dining

2.28

 dine

1.67

 dined

1.44

din

1.39

 Dine

1.31

Din

1.24

Dine

1.24

Activations Density 0.092%

references to dining or eating experiences

No Comments

No Known Activations