INDEX

Explanations

programming-related terms and keywords, particularly those related to functions and method declarations in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

 grotte

-0.46

 Cualquier

-0.46

 pter

-0.45

ிய

-0.44

-0.43

EZ

-0.43

ėd

-0.41

lag

-0.40

paw

-0.40

 başına

-0.40

POSITIVE LOGITS

 WaitForSeconds

1.70

 MethodInfo

1.56

 MainAxisSize

1.26

interopRequire

1.22

WaitGroup

1.20

 مشين

1.19

InSection

1.09

Datuak

1.07

RSpec

1.02

wpi

1.02

Activations Density 0.002%

programming-related terms and keywords, particularly those related to functions and method declarations in code

No Comments

No Known Activations