INDEX

Explanations

references to geopolitical entities and related events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 themſelves

-0.97

 fubject

-0.95

 raiſ

-0.87

 faſt

-0.86

</caption>

-0.85

 pleaſure

-0.83

 Houſe

-0.82

 juſt

-0.81

 Anſ

-0.81

 Monfieur

-0.80

POSITIVE LOGITS

 Bretagne

0.71

 تضيفلها

0.62

 porc

0.60

Sask

0.58

 Saudi

0.58

 Rhode

0.57

 Welsh

0.57

Dana

0.56

 Galway

0.56

 modo

0.56

Activations Density 1.442%

references to geopolitical entities and related events

No Comments

No Known Activations