INDEX

Explanations

references to job titles and roles within a professional context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

enumi

-0.42

 regolare

-0.42

 كومونز

-0.41

 հղումներ

-0.41

 Loops

-0.40

 régulière

-0.40

ineda

-0.38

strijden

-0.37

ronpa

-0.36

atouille

-0.36

POSITIVE LOGITS

 expert

0.59

 former

0.55

Worked

0.54

ViewImports

0.54

 Experten

0.52

expert

0.51

 expertise

0.51

 experts

0.50

 experto

0.49

 expertos

0.47

Activations Density 0.312%

references to job titles and roles within a professional context

No Comments

No Known Activations