INDEX

Explanations

technical and specialized terms, particularly in 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 @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

queryInterface

-0.55

aarrggbb

-0.49

횟

-0.47

 subsequently

-0.45

 iconFacebook

-0.43

nats

-0.43

fortawesome

-0.43

Encyclopædia

-0.43

 numerus

-0.42

 potentially

-0.42

POSITIVE LOGITS

Lähteet

0.96

 Roskov

0.69

úgó

0.67

newArrayList

0.64

gdx

0.64

 kasarigan

0.63

Välislingid

0.63

ագրություններ

0.63

әрмәләр

0.61

 >=",

0.60

Activations Density 1.633%

technical and specialized terms, particularly in programming and data structures

No Comments

No Known Activations