INDEX

Explanations

references to fields of study or areas of research

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

 decorativas

-0.91

 myſelf

-0.87

 Cæsar

-0.86

 Majefty

-0.86

 Unger

-0.85

 Monfieur

-0.83

 himſelf

-0.81

 navideñas

-0.80

 Rossetti

-0.78

 reaſon

-0.78

POSITIVE LOGITS

 field

2.56

 fields

2.40

 Field

2.39

 Fields

2.26

 FIELD

2.25

field

2.12

Field

2.12

fields

2.07

 getField

2.02

FIELD

1.99

Activations Density 0.075%

references to fields of study or areas of research

No Comments

No Known Activations