INDEX

Explanations

names and terms related to individuals and their roles or professions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

يكب

-0.57

 linkovi

-0.51

aville

-0.49

Tembelea

-0.48

ratto

-0.46

 оригіналу

-0.46

 étranger

-0.45

addComponent

-0.44

Jereo

-0.44

 weißem

-0.43

POSITIVE LOGITS

 MonoBehaviour

0.73

AndEndTag

0.63

serviceWorker

0.58

 pyplot

0.57

HostException

0.57

Життєпис

0.56

="#"><

0.55

ElementException

0.54

Geplaatst

0.54

 astore

0.53

Activations Density 0.231%

names and terms related to individuals and their roles or professions

No Comments

No Known Activations