INDEX

Explanations

elements related to programming logic and user interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 çerçe

-0.50

PostExecute

-0.50

 intStringLen

-0.48

 Nuss

-0.47

MessageOf

-0.47

AntiForgeryToken

-0.46

امة

-0.45

每月

-0.45

Annual

-0.44

ьаж

-0.44

POSITIVE LOGITS

 InputDecoration

0.68

 الحره

0.65

 initComponents

0.64

новниш

0.62

uertos

0.58

 Савезне

0.57

CppCodeGen

0.57

TacToe

0.54

nalités

0.54

nasse

0.54

Activations Density 0.942%

elements related to programming logic and user interaction

No Comments

No Known Activations