INDEX

Explanations

elements related to definitions and calculations in a programming or mathematical context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.94

 Meksiku

-0.87

 ProtoMessage

-0.79

Museum

-0.76

margin

-0.75

mother

-0.75

 Managers

-0.74

moisture

-0.74

 Manager

-0.74

Manager

-0.73

POSITIVE LOGITS

########.

0.44

 Chrif

0.43

delige

0.43

pyplot

0.42

endphp

0.42

Efq

0.41

ſelves

0.41

plink

0.41

ovico

0.41

 faſt

0.41

Activations Density 0.683%

elements related to definitions and calculations in a programming or mathematical context

No Comments

No Known Activations