INDEX

Explanations

scientific and technical terms related to research and methodology

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

клопе

-0.56

respected

-0.49

原始内容存档于

-0.48

honneur

-0.48

 Trust

-0.48

work

-0.47

 level

-0.45

ca

-0.45

StoredProcedure

-0.45

ColumnHeaders

-0.44

POSITIVE LOGITS

ArrowToggle

0.81

Efq

0.81

 chré

0.73

=?";

0.72

 Stedman

0.72

 Jefus

0.70

$_"

0.68

htbp

0.67

 vaut

0.66

 שוליים

0.66

Activations Density 2.463%

scientific and technical terms related to research and methodology

No Comments

No Known Activations