INDEX

Explanations

phrases relating to returning or coming back to a previous state or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

valently

-0.76

ברה

-0.74

ykite

-0.68

 Jill

-0.67

 cờ

-0.67

 Carlsbad

-0.66

 Dickens

-0.65

Farbe

-0.64

لية

-0.63

DaoImpl

-0.63

POSITIVE LOGITS

 RETURN

1.48

 Return

1.46

return

1.44

 returns

1.44

 Returns

1.38

 return

1.36

Return

1.34

eturn

1.30

 Returned

1.28

 returned

1.27

Activations Density 0.103%

phrases relating to returning or coming back to a previous state or location

No Comments

No Known Activations