INDEX

Explanations

mathematical symbols and notations used in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ੱ

-0.48

RLock

-0.45

 bragging

-0.45

Groet

-0.45

 endif

-0.45

â

-0.45

<0xEF>

-0.44

 keber

-0.44

 propTypes

-0.44

魁

-0.44

POSITIVE LOGITS

Попис

0.82

niająca

0.73

thâu

0.72

 Италијани

0.69

 "..\..\..\

0.68

 HttpNotFound

0.65

 ویکی‌پدی

0.63

WithIOException

0.61

intios

0.61

kháu

0.60

Activations Density 3.553%

mathematical symbols and notations used in equations

No Comments

No Known Activations