INDEX

Explanations

terms related to skills and expertise

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

"Skill" or "Skill Kyutama"

np_acts-logits-general · gemini-2.0-flash

skill Kyutama or skillset

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

parsedMessage

-0.99

djangoproject

-0.82

 Wikimedijinoj

-0.77

 légales

-0.76

NUMX

-0.73

bewerken

-0.71

)++;

-0.70

 Daarom

-0.70

 Audiodateien

-0.70

Personensuche

-0.67

POSITIVE LOGITS

 skills

1.07

 Skill

1.07

 skill

1.05

 Skills

1.05

skills

1.02

Skills

1.00

SKILL

0.95

skill

0.93

Skill

0.92

 SKILLS

0.84

Activations Density 0.078%

terms related to skills and expertise

"Skill" or "Skill Kyutama"

skill Kyutama or skillset

No Comments

No Known Activations