INDEX

Explanations

coding and programming-related warnings and directives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

DJANGO

-0.63

 दें

-0.58

scryfall

-0.58

 autorytatywna

-0.57

 løpet

-0.56

InstanceState

-0.56

Datuak

-0.55

htë

-0.54

XmlAccessType

-0.53

 участь

-0.52

POSITIVE LOGITS

 tslint

0.91

noinspection

0.85

 ReSharper

0.77

 pylint

0.74

 eslint

0.59

SuppressMessage

0.58

Hochspringen

0.55

eslint

0.54

DataAnnotations

0.52

AutoresizingMask

0.51

Activations Density 0.109%

coding and programming-related warnings and directives

No Comments

No Known Activations