INDEX

Explanations

terms related to various skills and competencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Reiche

-0.57

 Monteiro

-0.52

 reports

-0.47

 Berge

-0.46

 Leighton

-0.46

 Waugh

-0.45

 report

-0.45

})),

-0.44

 Carrington

-0.44

 Reports

-0.44

POSITIVE LOGITS

 Skill

1.55

 Skills

1.53

 skills

1.52

Skill

1.50

 skill

1.49

Skills

1.48

skills

1.47

 SKILLS

1.34

skill

1.34

SKILL

1.22

Activations Density 0.159%

terms related to various skills and competencies

No Comments

No Known Activations

terms related to various skills and competencies

No Comments

No Known Activations