INDEX

Explanations

terms related to electric charge and current

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 charge

-0.97

 charging

-0.90

 charged

-0.88

 Charging

-0.78

 Charge

-0.78

charge

-0.74

Charging

-0.74

 שוליים

-0.73

Charge

-0.72

 Charged

-0.71

POSITIVE LOGITS

GES

0.51

endwhile

0.50

исленность

0.49

InstanceState

0.46

_'.$

0.45

 neige

0.45

 plates

0.44

量的

0.44

 administrativa

0.44

="'.$

0.44

Activations Density 0.065%

terms related to electric charge and current

No Comments

No Known Activations