INDEX

Explanations

mathematical operators and function notations related to algebraic concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

OGND

-0.84

+#+#

-0.81

abestanden

-0.76

 AssemblyCompany

-0.73

 تانيه

-0.69

 EconPapers

-0.68

BorderFactory

-0.63

webElement

-0.63

 ویکی‌پدی

-0.62

IntoConstraints

-0.59

POSITIVE LOGITS

operatorname

0.77

 consultato

0.53

 FishBase

0.49

شوند

0.48

mogat

0.46

WriteLiteral

0.45

tako

0.42

 Boll

0.42

han

0.42

transQ

0.42

Activations Density 0.069%

mathematical operators and function notations related to algebraic concepts

No Comments

No Known Activations