INDEX

Explanations

programming-related terms and flags in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 يتيمه

-0.62

MathML

-0.56

 kaarangay

-0.54

//</

-0.54

+#+#

-0.51

 ProtoMessage

-0.51

AddTagHelper

-0.50

IsMutable

-0.50

AndEndTag

-0.50

EDEFAULT

-0.50

POSITIVE LOGITS

 acclaimed

0.63

flags

0.63

Flags

0.63

 Veter

0.63

Veteran

0.61

 Veteran

0.60

 Flag

0.58

 renowned

0.57

 Veterans

0.57

 Flags

0.57

Activations Density 1.709%

programming-related terms and flags in code

No Comments

No Known Activations

programming-related terms and flags in code

No Comments

No Known Activations