INDEX

Explanations

mathematical expressions formatted in alignment or array environments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

KommentareTeilen

-0.52

//

-0.49

Ant

-0.47

 Paglinawan

-0.47

PreferredItem

-0.46

ⓧ

-0.46

йн

-0.45

ppelin

-0.44

("

-0.44

transQ

-0.44

POSITIVE LOGITS

 nakalista

0.69

AxisAlignment

0.63

 consultato

0.61

 paroisse

0.61

出版年

0.60

AutoScale

0.60

XmlAccessorType

0.59

IsContent

0.59

ContentAsync

0.56

 hObject

0.56

Activations Density 0.110%

mathematical expressions formatted in alignment or array environments

No Comments

No Known Activations