INDEX

Explanations

patterns associated with variable declarations and assignments in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 InputDecoration

-0.84

IGraphics

-0.73

xial

-0.72

ftagPool

-0.70

lamic

-0.69

 Oakes

-0.67

 Pauly

-0.66

 Thine

-0.66

 axioms

-0.66

GEBURTS

-0.65

POSITIVE LOGITS

bitField

0.91

 defaultstate

0.90

 useState

0.67

 lateinit

0.62

useState

0.61

bonnet

0.52

BeginContext

0.51

AddressBook

0.49

initComponents

0.49

 onResponse

0.48

Activations Density 0.036%

patterns associated with variable declarations and assignments in programming code

No Comments

No Known Activations