INDEX

Explanations

references to supplementary information or additional data in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

farin

-0.73

 Wikispecies

-0.70

Климат

-0.68

ெ

-0.67

 helst

-0.62

enapa

-0.61

ENDIAN

-0.61

 Insee

-0.60

 Kalau

-0.60

Charset

-0.60

POSITIVE LOGITS

additional

1.80

 additional

1.79

Additional

1.77

 Additional

1.71

ADDITIONAL

1.66

 ADDITIONAL

1.59

Addition

1.26

ditional

1.26

追加

1.22

 Addition

1.20

Activations Density 0.111%

references to supplementary information or additional data in a document

No Comments

No Known Activations