INDEX

Explanations

references to legal or legislative processes and related numerical data

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 uninsured

-0.53

 MySpace

-0.53

 gainera

-0.50

 combinatorial

-0.50

svn

-0.49

țională

-0.49

iforms

-0.48

svn

-0.48

iseries

-0.48

POSITIVE LOGITS

principalColumn

0.76

kloped

0.68

unknownFields

0.67

ViewImports

0.66

withIdentifier

0.66

endpush

0.65

interopRequire

0.64

msgSender

0.64

 nullptr

0.60

ArgsConstructor

0.60

Activations Density 0.170%

references to legal or legislative processes and related numerical data

No Comments

No Known Activations