INDEX

Explanations

locations and descriptions of physical spaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.39.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

tagHelperRunner

-0.37

kháu

-0.37

łasz

-0.37

InitVars

-0.36

聞こ

-0.35

 snippetHide

-0.34

ownic

-0.33

cfs

-0.33

bindParam

-0.33

VYMaps

-0.33

POSITIVE LOGITS

 living

1.30

 dining

1.23

 kitchen

1.19

 bedroom

1.15

living

1.09

dining

1.07

 Living

1.02

 Dining

1.02

Living

1.00

Dining

1.00

Activations Density 0.291%

locations and descriptions of physical spaces

No Comments

No Known Activations

locations and descriptions of physical spaces

No Comments

No Known Activations