INDEX

Explanations

proper nouns, especially names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 noDo

-0.64

Personensuche

-0.62

 препратки

-0.60

richTextPanel

-0.57

 Roskov

-0.57

хьтан

-0.56

 nahilalakip

-0.55

tanleria

-0.53

 jspb

-0.48

rawDesc

-0.47

POSITIVE LOGITS

 BorderSide

0.46

 refroidissement

0.40

ształ

0.40

elerik

0.40

mamış

0.40

HtmlAttribute

0.38

 Einfluß

0.36

ContentLoaded

0.36

zde

0.36

 empresarial

0.36

Activations Density 0.363%

proper nouns, especially names of individuals

No Comments

No Known Activations