INDEX

Explanations

mathematical notations and symbols involving primes and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

%)$

-0.67

年

-0.56

Istorija

-0.55

IUrlHelper

-0.55

ława

-0.54

astify

-0.52

angliski

-0.51

getRuntime

-0.49

stateMutability

-0.49

จำ

-0.49

POSITIVE LOGITS

prime

0.95

)^{\

0.70

 hObject

0.67

thansa

0.66

ładka

0.62

SuccessListener

0.59

ennium

0.59

 prime

0.59

 Flamen

0.59

]^{\

0.58

Activations Density 0.195%

mathematical notations and symbols involving primes and equations

No Comments

No Known Activations