INDEX

Explanations

references to brain-related topics or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

참고

-0.60

 overras

-0.58

czeniu

-0.53

tout

-0.52

gypti

-0.50

 perche

-0.50

 Профиль

-0.50

 Сколько

-0.49

lorette

-0.49

ttu

-0.48

POSITIVE LOGITS

waves

0.77

 للمعارف

0.73

 Brain

0.66

 BRAIN

0.65

 brains

0.64

 насељу

0.63

endregion

0.62

 brain

0.62

 BorderRadius

0.62

 createState

0.62

Activations Density 0.125%

references to brain-related topics or conditions

No Comments

No Known Activations