INDEX

Explanations

references to "Padé approximants" and related concepts in mathematical contexts

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

]--;

-0.72

Kanpo

-0.60

 RequestMethod

-0.56

Tracce

-0.56

اظ

-0.53

kyou

-0.53

HomeAsUpEnabled

-0.52

 Kirke

-0.51

utilisons

-0.51

 suku

-0.51

POSITIVE LOGITS

Pad

0.65

Pad

0.65

PAD

0.64

 Pads

0.58

GEBURTSDATUM

0.57

PAD

0.56

__;

0.54

 AppColors

0.54

tagHelperRunner

0.53

 almofada

0.52

Activations Density 0.136%

references to "Padé approximants" and related concepts in mathematical contexts

No Comments

No Known Activations