INDEX

Explanations

terms and phrases related to programming and coding conventions, particularly around common coding vulnerabilities and standards

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 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

 Wissens

-0.53

cosx

-0.49

Erm

-0.48

ind

-0.48

Ind

-0.48

op

-0.47

RTDA

-0.47

 Kinders

-0.47

 опо

-0.46

coc

-0.46

POSITIVE LOGITS

AndroidJUnit

0.84

LookAnd

0.74

SpringBootTest

0.72

RenderAtEndOf

0.68

AutoScaleMode

0.68

typeparam

0.67

 Italijanski

0.67

webElementXpaths

0.65

webtoken

0.64

principalColumn

0.63

Activations Density 3.001%

terms and phrases related to programming and coding conventions, particularly around common coding vulnerabilities and standards

No Comments

No Known Activations