INDEX

Explanations

keywords and terms related to programming and software documentation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 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

FieldBuilder

-0.50

IndentedString

-0.48

AnchorStyles

-0.43

MessageTagHelper

-0.43

bitField

-0.42

 "..\..\

-0.39

 '\\;'

-0.37

orElseThrow

-0.36

 useAppContext

-0.35

TagHelper

-0.34

POSITIVE LOGITS

 Meksiku

0.86

 يتيمه

0.77

XmlAccessType

0.75

sizeCache

0.73

 فريبيس

0.71

 uLocal

0.69

 defStyleAttr

0.68

slidesToShow

0.66

NewUrlParser

0.66

outSlope

0.63

Activations Density 1.433%

keywords and terms related to programming and software documentation

No Comments

No Known Activations