INDEX

Explanations

technical terminology related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

تقاوى

-0.69

 bezeichneter

-0.64

SourceChecksum

-0.63

WithIdentifier

-0.60

RTCK

-0.60

aarrggbb

-0.56

KommentareTeilen

-0.56

tipp

-0.55

RegistryLite

-0.55

 autorytatywna

-0.54

POSITIVE LOGITS

Capítulo

0.56

MATIC

0.53

 urme

0.49

 Obedience

0.49

 Harlow

0.48

__":

0.47

 Buddha

0.47

PBS

0.46

 управління

0.46

 obedience

0.46

Activations Density 2.206%

technical terminology related to programming and data structures

No Comments

No Known Activations