INDEX

Explanations

warnings or instructions related to product usage and safety

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

+#+#

-0.59

expandindo

-0.52

Vtbl

-0.50

 messed

-0.49

 مشين

-0.48

 sendok

-0.47

 gyhoeddwyd

-0.47

RenderAtEndOf

-0.46

 illuminating

-0.46

 utafitiHapana

-0.46

POSITIVE LOGITS

پان

0.36

 Italijani

0.35

together

0.35

 aDecoder

0.34

 exer

0.34

ってください

0.34

queryInterface

0.33

 MyBatis

0.33

MIB

0.32

Sense

0.31

Activations Density 0.138%

warnings or instructions related to product usage and safety

No Comments

No Known Activations