INDEX

Explanations

references to physical and emotional urges, actions, and impulses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 estekak

-0.53

WillAppear

-0.50

urangan

-0.50

 trattato

-0.49

 conquered

-0.47

Jeografia

-0.47

 serviceable

-0.46

strecke

-0.46

MMV

-0.45

 trato

-0.45

POSITIVE LOGITS

 impulse

1.45

 urge

1.28

impulse

1.28

 impulses

1.18

 impuls

1.17

 Impulse

1.17

 impetus

1.15

 impulso

1.10

 urgency

1.06

Impulse

1.05

Activations Density 0.346%

references to physical and emotional urges, actions, and impulses

No Comments

No Known Activations