INDEX

Explanations

programming syntax and logical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

vil

-0.44

ف

-0.40

::_('

-0.39

tri

-0.39

uza

-0.39

ier

-0.39

="../

-0.38

("../

-0.38

“

-0.38

ensch

-0.37

POSITIVE LOGITS

 hObject

0.96

 Majefty

0.86

RegistryLite

0.85

 >=",

0.83

 resourceCulture

0.83

principalColumn

0.82

 ModelExpression

0.82

 StatefulWidget

0.81

 Roskov

0.81

EndGlobalSection

0.80

Activations Density 0.103%

programming syntax and logical expressions

No Comments

No Known Activations