INDEX

Explanations

references to scientific studies and their significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 Cæsar

-0.57

 calcareous

-0.52

 Einfluß

-0.51

 meiner

-0.50

ponses

-0.49

 glau

-0.49

 meines

-0.49

 herbaceous

-0.48

 Bewußt

-0.48

 anecd

-0.48

POSITIVE LOGITS

“

1.38

1.33

 “…

1.09

 "...

1.05

 “[

1.00

 “...

1.00

 könne

0.99

"[

0.98

«

0.98

 müsse

0.97

Activations Density 1.003%

references to scientific studies and their significance

No Comments

No Known Activations