INDEX

Explanations

mathematical notations or symbols related to estimation and functions

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

 contextLoads

-0.91

 Serr

-0.78

 Percival

-0.78

 disambiguazione

-0.76

 Pais

-0.76

 Manas

-0.75

Oke

-0.74

 DriverManager

-0.74

 entirety

-0.74

NECT

-0.74

POSITIVE LOGITS

hat

2.30

hat

2.24

Hat

2.20

Hat

2.09

 hats

2.06

HAT

1.99

HAT

1.78

 Hats

1.75

hats

1.70

Hats

1.56

Activations Density 0.124%

mathematical notations or symbols related to estimation and functions

No Comments

No Known Activations