INDEX

Explanations

mathematical or programming notation and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

nestjs

-0.45

ulman

-0.40

Autoritní

-0.36

nikahan

-0.36

mui

-0.35

kennung

-0.34

conscious

-0.34

∬

-0.34

لينكات

-0.34

nodoc

-0.34

POSITIVE LOGITS

addCriterion

0.72

Third

0.65

 third

0.64

THIRD

0.62

 Normdatei

0.59

 Third

0.59

第三

0.59

 üçün

0.59

third

0.58

RotationOrder

0.58

Activations Density 2.653%

mathematical or programming notation and expressions

No Comments

No Known Activations