INDEX

Explanations

mathematical terms and inequalities related to sequences and functions

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

曖昧さ回避

-0.52

 ujednoznacz

-0.52

脚注の使い方

-0.52

ModelAdmin

-0.50

 estekak

-0.49

 OMITTED

-0.47

身

-0.47

RegistryLite

-0.46

 مشين

-0.46

انيف

-0.46

POSITIVE LOGITS

<=

0.97

≤

0.89

<=

0.78

 <=",

0.76

 >=",

0.74

≤

0.74

leq

0.72

>=

0.71

≥

0.68

]<=

0.66

Activations Density 0.982%

mathematical terms and inequalities related to sequences and functions

No Comments

No Known Activations