INDEX

Explanations

terms related to content networking and computer science concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

Geplaatst

-0.77

Portail

-0.74

Inflater

-0.72

letoe

-0.72

GEBURTSDATUM

-0.72

berdayakan

-0.71

 mắn

-0.71

🏿

-0.70

 NDEBUG

-0.69

bleshooting

-0.69

POSITIVE LOGITS

getC

0.75

 getC

0.73

 Cary

0.70

cVar

0.69

CAC

0.68

cupertino

0.67

ColumnHeaders

0.66

 Chom

0.66

CCS

0.65

Activations Density 4.444%

terms related to content networking and computer science concepts

No Comments

No Known Activations