INDEX

Explanations

sequences of characters representing functions and variables in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

extAlignment

-0.80

 <>",

-0.77

LEncoder

-0.69

ItemBackground

-0.69

UpInside

-0.67

 StyleSheet

-0.67

^(@)

-0.66

ésult

-0.63

Xna

-0.63

 ویکی‌پدیا

-0.62

POSITIVE LOGITS

 Exacts

0.57

 kasarigan

0.54

Portail

0.54

verifyException

0.51

הערות

0.50

IUrlHelper

0.47

 مشين

0.47

 VIAF

0.46

writeObject

0.45

bsen

0.45

Activations Density 0.374%

sequences of characters representing functions and variables in programming languages

No Comments

No Known Activations