INDEX

Explanations

elements related to method calls or function invocations in programming

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

programming method calls

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

 Administrativna

-0.93

IntoConstraints

-0.72

 propOrder

-0.70

tagHelperRunner

-0.68

Sucesor

-0.67

ValueStyle

-0.66

 незавершена

-0.64

 мәкал

-0.64

 intptr

-0.63

 ModelExpression

-0.60

POSITIVE LOGITS

Fle

0.49

 abgerufen

0.47

 proveedores

0.46

 toString

0.45

 Anges

0.45

 CharSequence

0.43

Hau

0.43

Iterator

0.43

sty

0.41

сия

0.41

Activations Density 0.037%

elements related to method calls or function invocations in programming

programming method calls

No Comments

No Known Activations