INDEX

Explanations

directional terms related to navigation or location

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

providedIn

-0.96

 незавершена

-0.85

expandindo

-0.82

DoubleQuotes

-0.82

RectangleBorder

-0.82

))));

-0.73

})*/

-0.71

))){

-0.71

/></

-0.69

TagMode

-0.69

POSITIVE LOGITS

 north

2.15

 south

2.10

 east

1.83

 west

1.64

north

1.62

south

1.53

 northwest

1.33

 northward

1.28

 southeast

1.27

 southward

1.26

Activations Density 0.121%

directional terms related to navigation or location

No Comments

No Known Activations