INDEX

Explanations

references to locations, particularly the United States and the Dominican Republic

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

:])

-0.58

kháu

-0.55

 électroniques

-0.54

Przypisy

-0.54

ものです

-0.52

 iprot

-0.52

 behalf

-0.50

SourceChecksum

-0.48

 nakalista

-0.47

庁

-0.47

POSITIVE LOGITS

 United

0.99

United

0.80

 Philippines

0.78

 Netherlands

0.78

USA

0.72

 متحده

0.71

 Verenigde

0.68

 suburbs

0.68

 Egyes

0.67

DockStyle

0.67

Activations Density 0.261%

references to locations, particularly the United States and the Dominican Republic

No Comments

No Known Activations