INDEX

Explanations

references to locations related to homes or residences

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

NonNull

-0.42

océan

-0.37

 gången

-0.36

 totally

-0.35

 release

-0.35

ーリー

-0.34

ShortName

-0.34

 uniform

-0.34

 Parcelable

-0.34

 finally

-0.33

POSITIVE LOGITS

 home

0.98

 hogar

0.97

 household

0.95

 otthon

0.90

 house

0.90

 households

0.89

household

0.88

 homes

0.86

🏡

0.86

 rumah

0.85

Activations Density 0.279%

references to locations related to homes or residences

No Comments

No Known Activations