INDEX

Explanations

terms related to evaluation and assessment 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Numerology

-0.46

graphiques

-0.43

 tayo

-0.43

 udaler

-0.43

vár

-0.41

 conlle

-0.41

kin

-0.41

-0.40

 prioritized

-0.39

цент

-0.39

POSITIVE LOGITS

 estekak

0.85

__":

0.80

IVEREF

0.80

 Infórmanos

0.77

DispatchToProps

0.73

LLocation

0.65

?>">

0.65

 الرياضيه

0.64

SequentialGroup

0.63

__':

0.63

Activations Density 0.454%

terms related to evaluation and assessment in various contexts

No Comments

No Known Activations