INDEX

Explanations

mathematical notation indicating derivatives and vector notation

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

jillo

-0.59

 Erwart

-0.56

ม้

-0.54

siąż

-0.52

jsxFileName

-0.52

 Airtel

-0.51

őd

-0.50

 itself

-0.49

 Estonia

-0.49

LayoutStyle

-0.47

POSITIVE LOGITS

 Major

0.94

 MAJOR

0.93

Major

0.92

major

0.91

 major

0.86

MAJ

0.84

MAJ

0.83

MAJOR

0.82

Maj

0.81

maj

0.81

Activations Density 0.061%

mathematical notation indicating derivatives and vector notation

No Comments

No Known Activations