INDEX

Explanations

's binding and linking terminology in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

+#+

-0.89

</s>

-0.74

 Alvaro

-0.72

printStackTrace

-0.72

 Thessalon

-0.72

 betweenstory

-0.71

abestanden

-0.70

beforeEach

-0.69

addContainerGap

-0.68

serviceWorker

-0.67

POSITIVE LOGITS

 Bind

1.72

 BIND

1.62

 binding

1.62

 Binding

1.61

 bind

1.57

 binds

1.55

 bindings

1.46

binding

1.45

Bind

1.44

bind

1.42

Activations Density 0.089%

's binding and linking terminology in a programming context

No Comments

No Known Activations