INDEX

Explanations

references to "extensions" and their various forms in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 typelib

-0.73

Obrázky

-0.65

writerow

-0.64

^(@)

-0.64

setLayoutManager

-0.64

 useRouter

-0.63

VersionUID

-0.63

messageInfo

-0.62

IsPostBack

-0.62

mbggenerated

-0.61

POSITIVE LOGITS

 extension

1.76

Extension

1.72

 Extension

1.72

Ext

1.72

ext

1.70

EXT

1.65

EXT

1.64

ext

1.58

Ext

1.52

 extensions

1.51

Activations Density 0.204%

references to "extensions" and their various forms in a technical context

No Comments

No Known Activations