INDEX

Explanations

lines related to defining and checking attributes or properties in programming contexts

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

Portály

-0.54

kiet

-0.50

 šť

-0.48

 Obrador

-0.45

jooq

-0.45

Chất

-0.44

ędzynarod

-0.43

 adelantado

-0.42

 admiten

-0.42

casio

-0.42

POSITIVE LOGITS

Datuak

0.61

MigrationBuilder

0.60

kloped

0.60

 الحره

0.58

 combineReducers

0.58

 simplifié

0.58

saraba

0.57

ObjectMeta

0.57

 UserController

0.56

setVerticalGroup

0.56

Activations Density 0.222%

lines related to defining and checking attributes or properties in programming contexts

No Comments

No Known Activations