INDEX

Explanations

references to decreases or drops in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

autoFocus

-0.37

raits

-0.37

¤

-0.36

setOnItem

-0.35

cedure

-0.34

 riveting

-0.34

<mask>

-0.34

 keyword

-0.33

 egyszer

-0.33

empor

-0.33

POSITIVE LOGITS

 descending

1.34

 lowered

1.31

 drop

1.31

 decline

1.29

 caída

1.28

 falling

1.26

 downward

1.26

Falling

1.24

 lowering

1.24

 fall

1.24

Activations Density 1.702%

references to decreases or drops in various contexts

No Comments

No Known Activations