INDEX

Explanations

details related to locations and measurements in a building

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

维生素

-0.46

 comuniques

-0.45

 अभ

-0.42

からず

-0.38

bindParam

-0.36

ve

-0.36

sság

-0.36

 statement

-0.36

 item

-0.36

POSITIVE LOGITS

 ground

1.59

 upstairs

1.54

 basement

1.43

 downstairs

1.43

ground

1.40

 Ground

1.35

 GROUND

1.31

Ground

1.31

 floor

1.30

 floors

1.25

Activations Density 0.093%

details related to locations and measurements in a building

No Comments

No Known Activations