INDEX

Explanations

references to articles and publications

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

XCTAssertEqual

-0.51

 outstanding

-0.51

 independent

-0.49

 respective

-0.48

 sacco

-0.48

ri

-0.47

 manner

-0.46

 separate

-0.46

 particular

-0.46

↵↵

-0.45

POSITIVE LOGITS

TypedDataSet

1.05

PerformLayout

0.98

 itſelf

0.92

 produkter

0.91

脚注の使い方

0.85

 EconPapers

0.85

lgari

0.83

 мәкал

0.83

 للمعارف

0.82

Демографія

0.80

Activations Density 0.233%

references to articles and publications

No Comments

No Known Activations