INDEX

Explanations

references to database terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 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

KURZBESCHREIBUNG

-0.67

)))));

-0.63

ArgumentParser

-0.62

)));

-0.58

--

-0.57

erequisite

-0.52

 encar

-0.52

Encyklopedia

-0.52

)}

-0.51

ViewStyle

-0.50

POSITIVE LOGITS

Press

1.00

 Press

0.92

press

0.90

 تضيفلها

0.86

PRESS

0.85

db

0.84

 Experiment

0.83

 PRESS

0.79

DB

0.73

 Experiments

0.72

Activations Density 0.133%

references to database terminology

No Comments

No Known Activations