INDEX

Explanations

mentions of notes or annotations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Brito

-0.70

 Архивировано

-0.68

Perché

-0.63

 consum

-0.62

ிரு

-0.62

 DriverManager

-0.60

Académie

-0.60

Vla

-0.59

StrictEqual

-0.59

 Almeida

-0.59

POSITIVE LOGITS

 notes

1.59

 note

1.57

 Notes

1.56

 NOTE

1.51

 Note

1.46

 NOTES

1.39

 Nota

1.37

notes

1.32

note

1.31

Note

1.30

Activations Density 0.096%

mentions of notes or annotations

No Comments

No Known Activations