INDEX

Explanations

phrases that indicate potential outcomes or results of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.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

GEBURTSDATUM

-0.53

Controllo

-0.41

 PROGRESS

-0.40

omores

-0.39

COUNTER

-0.39

 progres

-0.39

برها

-0.38

WindowConstants

-0.38

 aapt

-0.37

IANGLES

-0.37

POSITIVE LOGITS

 akár

0.70

 parfois

0.61

 potentially

0.60

 Umständen

0.60

 sometimes

0.59

aarrggbb

0.57

 peuvent

0.55

 võib

0.55

 fometimes

0.54

 może

0.53

Activations Density 0.433%

phrases that indicate potential outcomes or results of actions

No Comments

No Known Activations