INDEX

Explanations

references to different aspects or types of energy

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

Vezi

-0.44

 muñecas

-0.44

 muñ

-0.40

 rosca

-0.39

 vorder

-0.36

baikan

-0.35

 Absch

-0.34

oyn

-0.34

 Bupati

-0.34

 Distrito

-0.34

POSITIVE LOGITS

 energy

2.11

Energy

2.06

 Energy

2.05

energy

2.00

 ENERGY

1.94

ENERGY

1.90

 energia

1.69

 Energie

1.65

 energía

1.60

 énergie

1.56

Activations Density 0.078%

references to different aspects or types of energy

No Comments

No Known Activations