INDEX

Explanations

references to the location Washington

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

mögens

-0.72

CreateMap

-0.72

oredCriteria

-0.70

 aard

-0.67

bootstrapcdn

-0.67

DataMember

-0.66

 Vermögens

-0.66

 Neel

-0.65

 Chennai

-0.65

Moor

-0.64

POSITIVE LOGITS

 Washington

2.07

Washington

1.95

 WASHINGTON

1.66

 washington

1.58

WASHINGTON

1.54

washington

1.33

 Washing

1.28

 WASH

1.14

 Wash

1.07

WASH

1.07

Activations Density 0.052%

references to the location Washington

No Comments

No Known Activations