INDEX

Explanations

code-related keywords and configuration elements typically associated with programming or software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

\}\\

-0.52

")->

-0.52

 săptăm

-0.50

 следова

-0.49

罢了

-0.48

 sondern

-0.48

 recev

-0.48

 بلکه

-0.48

 quelcon

-0.47

Sucesor

-0.47

POSITIVE LOGITS

||

1.34

||

1.07

??

1.00

?:

0.96

0.81

||=

0.80

or

0.77

??

0.76

?:

0.75

||

0.67

Activations Density 0.142%

code-related keywords and configuration elements typically associated with programming or software development

No Comments

No Known Activations