INDEX

Explanations

programming concepts, particularly related to annotations, types, and code structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ViewImports

-0.82

 sumpay

-0.66

 Roskov

-0.65

bootstrapcdn

-0.61

 surla

-0.60

ReusableCell

-0.59

دانشنامهٔ

-0.57

يته

-0.55

 ***!

-0.55

AutoScale

-0.55

POSITIVE LOGITS



0.60

InputTagHelper

0.59

TagMode

0.56

vedic

0.53

ichthys

0.52

Personendaten

0.50

SourceChecksum

0.49

::_('

0.48

awaiter

0.48

</strong>

0.48

Activations Density 0.005%

programming concepts, particularly related to annotations, types, and code structure

No Comments

No Known Activations