INDEX

Explanations

terms related to computational graph theory and its properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.80

 mắn

-0.77

Geplaatst

-0.73

 useNavigate

-0.67

Rapport

-0.67

letoe

-0.66

撇

-0.65

 Rapport

-0.63

antaranya

-0.62

 uſed

-0.61

POSITIVE LOGITS

CCS

0.91

CQ

0.89

CBR

0.86

CCL

0.83

 Cots

0.83

CEC

0.83

 getC

0.82

Cn

0.81

Cey

0.81

Cok

0.81

Activations Density 5.552%

terms related to computational graph theory and its properties

No Comments

No Known Activations