INDEX

Explanations

phrases related to positive outcomes and improvements

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

SharedDtor

-0.53

ⓧ

-0.51

 étoient

-0.49

Vidite

-0.48

MockBean

-0.44

IsContent

-0.43

 bambú

-0.43

 indígen

-0.43

ſelben

-0.43

 سكانية

-0.43

POSITIVE LOGITS

 rewarding

0.40

 worth

0.38

AddHtmlAttribute

0.38

 benefit

0.36

0.35

 AssemblyVersion

0.35

 considérons

0.34

 benefits

0.33

 cleared

0.32

sträger

0.32

Activations Density 0.277%

phrases related to positive outcomes and improvements

No Comments

No Known Activations