INDEX

Explanations

references to technicians and their roles or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ibouti

-0.56

brid

-0.55

Hav

-0.53

 esca

-0.51

ינו

-0.50

 Приступљено

-0.50

</em>

-0.49

 uplifting

-0.48

 defaultstate

-0.47

 FetchType

-0.46

POSITIVE LOGITS

SharedCtor

1.05

 étoient

0.83

 uſed

0.83

 myſelf

0.82

 avoient

0.81

 étoit

0.81

 tombé

0.78

 feroit

0.78

 auroit

0.78

 pouvoit

0.77

Activations Density 0.089%

references to technicians and their roles or actions

No Comments

No Known Activations