INDEX

Explanations

mathematical notation and operations related to equations

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

 itſelf

-0.96

 myſelf

-0.94

Eſ

-0.93

 Reſ

-0.90

 iſt

-0.90

Efq

-0.88

 Houſe

-0.87

URLException

-0.86

 ſeveral

-0.84

 Jefus

-0.83

POSITIVE LOGITS

 للمعارف

0.49

...

0.49

0.48

 forteller

0.45

+#+

0.44

Bo

0.44

My

0.43

bo

0.43

 membuatnya

0.43

Activations Density 0.882%

mathematical notation and operations related to equations

No Comments

No Known Activations