INDEX

Explanations

references to object-oriented programming constructs such as "this" or "self"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Tikang

-0.52

 Meksiku

-0.44

 ciência

-0.44

getBoolean

-0.41

 Georgie

-0.41

 Stellung

-0.40

 vastaan

-0.40

vény

-0.39

rops

-0.39

config

-0.38

POSITIVE LOGITS

awtextra

0.69

Hauptartikel

0.69

Становништво

0.69

posables

0.68

WebVitals

0.67

featureID

0.67

 AssemblyCompany

0.65

niająca

0.63

 jScrollPane

0.63

Mockito

0.61

Activations Density 0.029%

references to object-oriented programming constructs such as "this" or "self"

No Comments

No Known Activations