INDEX

Explanations

coding-related terms and method calls related to user interface and data models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AndEndTag

-1.07

 AssemblyProduct

-1.05

 defaultstate

-1.00

 typelib

-0.96

 Administrativna

-0.90

 ResourceManager

-0.90

InjectAttribute

-0.89

 Baillargeon

-0.87

HtmlAttribute

-0.87

StructEnd

-0.86

POSITIVE LOGITS

RunAsync

1.24

stdc

0.88

ValueStyle

0.69

zA

0.67

AxisAlignment

0.64

viewDidLoad

0.64

makeText

0.63

AddHtmlAttribute

0.61

la

0.58

0.57

Activations Density 0.002%

coding-related terms and method calls related to user interface and data models

No Comments

No Known Activations