INDEX

Explanations

technical terms and phrases related to processes and implementations

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

 ро

-0.35

 fires

-0.35

msub

-0.34

bl

-0.32

CBE

-0.32

士

-0.32

 trous

-0.31

 kant

-0.31

 Beim

-0.30

Mor

-0.30

POSITIVE LOGITS

CloseOperation

0.78

IntOverflow

0.66

 AssemblyCulture

0.62

OGND

0.60

awaiter

0.60

SceneManagement

0.60

BufferException

0.59

 nahilalakip

0.58

 Paglinawan

0.55

GEBURTSDATUM

0.54

Activations Density 1.105%

technical terms and phrases related to processes and implementations

No Comments

No Known Activations