INDEX

Explanations

terms related to skills and abilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 EconPapers

-0.50

 Bost

-0.48

 Lath

-0.46

endregion

-0.42

AndEndTag

-0.41

retario

-0.40

 Pich

-0.39

 متح

-0.39

 Hale

-0.39

 Pacheco

-0.39

POSITIVE LOGITS

 skill

3.95

 Skill

3.59

skill

3.52

Skill

3.50

 skills

2.95

 Skills

2.80

skills

2.73

SKILL

2.70

Skills

2.67

 SKILLS

2.34

Activations Density 0.069%

terms related to skills and abilities

No Comments

No Known Activations