INDEX

Explanations

numerical values related to sizes or dimensions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Izvori

-0.63

Lycka

-0.61

MemoryWarning

-0.54

IContainer

-0.52

ẾT

-0.52

parseColor

-0.52

PAIGN

-0.51

chequer

-0.51

 TimeUnit

-0.50

uldron

-0.50

POSITIVE LOGITS

Size

0.89

 Size

0.75

yntaxException

0.73

UrlResolution

0.70

SocketChannel

0.69

 SIZE

0.67

 BorderSide

0.63

 InputDecoration

0.62

SIZE

0.61

size

0.60

Activations Density 0.009%

numerical values related to sizes or dimensions

No Comments

No Known Activations