INDEX

Explanations

terms related to success and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

reactstrap

-0.73

 Neri

-0.65

Jar

-0.63

ędzy

-0.60

θεν

-0.58

zmir

-0.57

 Portail

-0.56

 Bote

-0.56

▪️

-0.56

reactivex

-0.55

POSITIVE LOGITS

 success

2.99

 Success

2.74

Success

2.59

 SUCCESS

2.46

success

2.46

 successes

2.30

SUCCESS

2.21

 succès

2.14

 sucess

2.03

 éxito

2.00

Activations Density 0.058%

terms related to success and achievements

No Comments

No Known Activations