INDEX

Explanations

phrases and terms related to turning devices on and off

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

󠁢

-0.38

 grail

-0.38

 Acme

-0.38

verlauf

-0.37

 Karls

-0.36

Sif

-0.34

Speedy

-0.34

+#+

-0.34

スカ

-0.34

 terecht

-0.34

POSITIVE LOGITS

 encendido

0.71

 encender

0.70

 shutdown

0.68

 SwitchCompat

0.66

 shutting

0.65

 shut

0.65

 روشن

0.60

 OnEnable

0.60

 isEnabled

0.60

 shuts

0.60

Activations Density 0.407%

phrases and terms related to turning devices on and off

No Comments

No Known Activations