INDEX

Explanations

terms related to decoration and decorative elements

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

 AssemblyCulture

-0.98

ंदीखरीदारी

-0.87

berdayakan

-0.86

 picioare

-0.84

findpost

-0.82

 fathoms

-0.82

 Fidel

-0.81

WriteBarrier

-0.79

EndInit

-0.79

 unknownFields

-0.78

POSITIVE LOGITS

decor

1.46

Decor

1.42

 decorating

1.39

 decoration

1.38

 decorate

1.38

 decor

1.35

Decorator

1.35

 Decorate

1.33

 Decor

1.33

 DECOR

1.29

Activations Density 0.085%

terms related to decoration and decorative elements

No Comments

No Known Activations