INDEX

Explanations

references to connectivity and user input in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ftagPool

-0.75

 étoient

-0.66

berdayakan

-0.61

UnusedPrivate

-0.61

 ainfi

-0.60

VYMaps

-0.57

 tää

-0.57

 miniaturka

-0.55

 avoient

-0.55

 ModelExpression

-0.54

POSITIVE LOGITS

zum

1.36

 към

1.34

aos

1.33

zur

1.30

 إلى

1.29

zu

1.29

 đến

1.27

 به

1.25

à

1.24

 kepada

1.24

Activations Density 0.075%

references to connectivity and user input in programming contexts

No Comments

No Known Activations