INDEX

Explanations

references to tours or guided experiences

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

"tours"

np_acts-logits-general · gemini-2.0-flash

tour

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 resourceCulture

-0.64

AndEndTag

-0.61

 незавершена

-0.60

()]);

-0.57

}))

-0.54

boxer

-0.53

]}

-0.52

 Taktlose

-0.51

WireFormatLite

-0.49

FunctionFlags

-0.49

POSITIVE LOGITS

 tour

2.25

 tours

2.16

tour

1.83

 Tour

1.82

Tour

1.80

 Tours

1.74

Tours

1.72

 toured

1.69

tours

1.65

 TOUR

1.63

Activations Density 0.126%

references to tours or guided experiences

"tours"

tour

No Comments

No Known Activations