INDEX

Explanations

version numbers and their formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 IBOutlet

-0.74

stateProvider

-0.73

SequentialGroup

-0.72

abestanden

-0.67

AnchorStyles

-0.66

 ostavi

-0.66

StreetMap

-0.65

WriteLiteral

-0.64

GraphicsUnit

-0.63

Vanjske

-0.63

POSITIVE LOGITS

 versions

0.57

 版本

0.55

 Version

0.54

ByVersion

0.52

 anta

0.50

صدار

0.50

 Versions

0.49

'>=

0.48

 productName

0.47

 version

0.46

Activations Density 0.562%

version numbers and their formats

No Comments

No Known Activations