INDEX

Explanations

references to technical specifications and detailed information about software or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

-0.84

 Māori

-0.80

Ō

-0.79

β

-0.78

α

-0.78

 résumé

-0.76

-0.75

−

-0.74

Mā

-0.74

POSITIVE LOGITS

 doesnt

0.46

--

0.46

 didnt

0.45

 childrens

0.43

 Womens

0.43

 wasnt

0.43

 isnt

0.41

 arent

0.41

 womens

0.40

 Dont

0.40

Activations Density 15.158%

references to technical specifications and detailed information about software or systems

No Comments

No Known Activations