INDEX

Explanations

references to Canadian media, television networks, and related regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Tikang

-0.81

 للاسماء

-0.81

 customised

-0.80

alised

-0.80

personalised

-0.80

Ещё

-0.77

 authorisation

-0.76

 privatisation

-0.76

 personalisation

-0.76

authorised

-0.76

POSITIVE LOGITS

 Canadian

1.40

 Canada

1.40

 Canadians

1.32

Canada

1.28

 Canadá

1.23

Canadian

1.23

 CANADA

1.18

 Kanada

1.13

 canad

1.11

 canadi

1.11

Activations Density 0.101%

references to Canadian media, television networks, and related regulations

No Comments

No Known Activations