INDEX

Explanations

identifiers for interfaces and data structures in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

aarrggbb

-0.65

 autorytatywna

-0.63

 AssemblyCulture

-0.61

thâu

-0.59

-------------</

-0.57

 pinulongan

-0.56

WireFormatLite

-0.56

 protoimpl

-0.53

 HasFactory

-0.53

InputBorder

-0.51

POSITIVE LOGITS

0.64

interfaces

0.56

ICom

0.55

Gru

0.51

 IConfiguration

0.50

IT

0.50

 Rath

0.48

 Australian

0.48

 IERC

0.48

 Herr

0.46

Activations Density 0.258%

identifiers for interfaces and data structures in programming

No Comments

No Known Activations