INDEX

Explanations

specific mathematical names, terms, and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

YO

-0.47

 createContext

-0.45

Eko

-0.44

 Dene

-0.44

YG

-0.44

 Soro

-0.44

 Clínica

-0.43

Obrázky

-0.43

χεία

-0.43

 colorless

-0.42

POSITIVE LOGITS

 intptr

0.69

MigrationBuilder

0.68

internalType

0.66

StoreMessageInfo

0.66

 متعلقه

0.64

 onOptions

0.62

جستارهای

0.61

 فريبيس

0.61

antMatchers

0.60

ThemeOverlay

0.59

Activations Density 1.668%

specific mathematical names, terms, and references

No Comments

No Known Activations