INDEX

Explanations

occurrences of the word "work" and its variations

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

istoitu

-0.63

 pingente

-0.63

 cadeia

-0.60

Sagittarius

-0.53

 capuz

-0.50

sidemargin

-0.50

 mídia

-0.50

retudo

-0.49

detectChanges

-0.48

SharedCtor

-0.48

POSITIVE LOGITS

Work

1.24

 Work

1.17

 work

1.12

work

1.06

 WORK

1.02

WORK

1.00

Working

0.92

working

0.90

 working

0.89

 Arbeit

0.84

Activations Density 0.169%

occurrences of the word "work" and its variations

No Comments

No Known Activations