INDEX

Explanations

terminology related to crossing boundaries or conducting examinations in a research context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

QMetaType

-0.57

ArgsConstructor

-0.56

iyle

-0.55

usercontent

-0.54

 piú

-0.52

FormTagHelper

-0.52

zono

-0.50

BeforeMethod

-0.49

 moeite

-0.48

anasia

-0.48

POSITIVE LOGITS

 EconPapers

0.78

xel

0.68

principalColumn

0.67

WICH

0.65

 Cros

0.64

InitVars

0.63

 noDo

0.63

 useEffect

0.62

belast

0.62

Redacción

0.62

Activations Density 0.104%

terminology related to crossing boundaries or conducting examinations in a research context

No Comments

No Known Activations