INDEX

Explanations

mathematical notations and formulas related to model definitions

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

↵↵

-0.92

</b>

-0.65

<h2>

-0.65

<i>

-0.62

Â

-0.60

↵

-0.57

â

-0.55

↵↵↵

-0.54

-0.53

POSITIVE LOGITS

исленность

0.98

出版年

0.89

Personensuche

0.85

ințe

0.82

例句

0.78

kháu

0.76

ționale

0.74

jsonwebtoken

0.71

 hinweg

0.71

󠁿

0.71

Activations Density 0.405%

mathematical notations and formulas related to model definitions

No Comments

No Known Activations