INDEX

Explanations

technical terminology related to processes, changes, and interactions in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

astanza

-0.66

 ✭✭

-0.59

ignants

-0.56

GetAxis

-0.54

NSError

-0.54

 protoimpl

-0.53

AllAfrica

-0.52

 مشارکت‌کنندگان

-0.52

endroit

-0.51

testens

-0.51

POSITIVE LOGITS

 occurrence

0.55

 χρήση

0.53

 utilization

0.50

 utilisation

0.49

liferation

0.49

 detection

0.48

 creation

0.47

 emergence

0.46

 introduction

0.46

lification

0.46

Activations Density 0.862%

technical terminology related to processes, changes, and interactions in scientific contexts

No Comments

No Known Activations