INDEX

Explanations

geographical locations and their descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 makeStyles

-0.56

ďaka

-0.55

DebuggerNonUser

-0.54

derung

-0.54

原始内容存档于

-0.53

 defStyle

-0.53

 SafeMath

-0.52

 InputDecoration

-0.51

endpush

-0.51

 дописавши

-0.51

POSITIVE LOGITS

 near

1.31

 close

1.09

 approximately

1.05

 nearer

1.05

 closer

1.03

 Near

1.00

near

0.98

 miles

0.97

 halfway

0.95

 cerca

0.94

Activations Density 0.227%

geographical locations and their descriptions

No Comments

No Known Activations