INDEX

Explanations

references to software updates and improvements

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

])):

-0.59

]<<

-0.58

 Theſe

-0.52

 utafitiHapana

-0.51

]<<"

-0.49

öscht

-0.49

 rouleau

-0.49

TRIBUT

-0.48

()<<

-0.48

 Beſ

-0.47

POSITIVE LOGITS

出版年

0.73

 also

0.72

 EClass

0.68

تقاوى

0.64

 just

0.61

 still

0.60

″]

0.59

 nemlig

0.59

 already

0.58

 indeed

0.57

Activations Density 0.033%

references to software updates and improvements

No Comments

No Known Activations