INDEX

Explanations

keywords related to methods in programming, specifically those associated with void functions and method definitions

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

programming function starters

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

CGContext

-0.62

 ujednoznacz

-0.59

runApp

-0.56

guisement

-0.55

Trả

-0.54

glEnd

-0.52

 ApiException

-0.50

multer

-0.50

alló

-0.50

 vVar

-0.50

POSITIVE LOGITS

ViewFeatures

0.75

enumi

0.75

 Picchu

0.73

_)

0.66

erton

0.63

AccessorTable

0.63

ettes

0.61

awtextra

0.61

](#

0.60

 Inner

0.60

Activations Density 0.013%

keywords related to methods in programming, specifically those associated with void functions and method definitions

programming function starters

No Comments

No Known Activations