INDEX

Explanations

terms related to statistical analysis and graphical models

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.76

 useNavigate

-0.72

berdayakan

-0.69

 Rapport

-0.67

 mắn

-0.66

Rapport

-0.66

letoe

-0.66

 uſed

-0.65

撇

-0.64

 SDLK

-0.63

POSITIVE LOGITS

 getC

0.88

getC

0.84

CCS

0.80

CQ

0.79

Cs

0.77

CCC

0.76

CCC

0.76

Coo

0.75

cupertino

0.75

classnames

0.75

Activations Density 3.930%

terms related to statistical analysis and graphical models

No Comments

No Known Activations