INDEX

Explanations

references to intelligence or agencies related to intelligence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

gro

-0.59

Gro

-0.56

Hol

-0.55

lat

-0.54

Wol

-0.54

Ham

-0.53

pas

-0.53

pr

-0.52

 yellow

-0.52

vir

-0.52

POSITIVE LOGITS

competent

0.98

 competence

0.93

 Competence

0.93

 competent

0.82

Compet

0.81

 compétence

0.79

 Fähigkeit

0.77

 Kompetenz

0.75

capable

0.73

 competente

0.73

Activations Density 0.468%

references to intelligence or agencies related to intelligence

No Comments

No Known Activations

references to intelligence or agencies related to intelligence

No Comments

No Known Activations