INDEX

Explanations

phrases that indicate notable developments or milestones in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 تانيه

-0.53

 joaat

-0.53

enumii

-0.52

tahankan

-0.49

urent

-0.48

bibitem

-0.47

BagConstraints

-0.47

 originais

-0.46

 fidé

-0.46

hibe

-0.45

POSITIVE LOGITS

finally

0.83

 finally

0.82

 FINALLY

0.75

 endlich

0.72

 finalmente

0.70

 enfin

0.69

 otomatig

0.67

ftagPool

0.62

:✨

0.62

FINALLY

0.61

Activations Density 0.472%

phrases that indicate notable developments or milestones in various contexts

No Comments

No Known Activations