INDEX

Explanations

phrases that describe layering or placement of objects, particularly in a culinary or structural context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 RemoteException

-0.56

MigrationBuilder

-0.54

 ligiloj

-0.42

 الرياضيه

-0.40

 nød

-0.39

 liitty

-0.39

 liik

-0.38

 entrées

-0.38

 læng

-0.38

为止

-0.38

POSITIVE LOGITS

 overlay

0.84

 overlays

0.72

overlay

0.72

 Overlay

0.71

Overlay

0.69

 OVER

0.65

 over

0.62

 overlaid

0.61

 encima

0.60

 върху

0.60

Activations Density 0.270%

phrases that describe layering or placement of objects, particularly in a culinary or structural context

No Comments

No Known Activations