INDEX

Explanations

references to wisdom and wise individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 NDEBUG

-0.72

 Roskov

-0.69

 estekak

-0.66

 ProtoMessage

-0.64

 officiels

-0.64

 Archi

-0.64

 typelib

-0.63

ResponseWriter

-0.62

antism

-0.61

 morrer

-0.59

POSITIVE LOGITS

 wise

1.70

 Wise

1.58

 wisdom

1.50

Wise

1.47

wise

1.42

 WISE

1.27

wisdom

1.24

 wiser

1.23

WISE

1.17

 meaningful

1.15

Activations Density 0.043%

references to wisdom and wise individuals

No Comments

No Known Activations