INDEX

Explanations

technical terms and concepts related to programming and memory issues

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

श्न

-0.52

chuga

-0.52

wußt

-0.50

Tracce

-0.47

 البريط

-0.47

通販

-0.46

mlı

-0.46

 الأمريكية

-0.46

 suivantes

-0.45

carpa

-0.45

POSITIVE LOGITS

 OFDb

0.70

ViewFeatures

0.67

 Infórmanos

0.61

 متعلقه

0.60

الحياه

0.60

tvguidetime

0.60

UrlResolution

0.60

 Monfieur

0.60

 intrins

0.58

 AssemblyCulture

0.58

Activations Density 0.057%

technical terms and concepts related to programming and memory issues

No Comments

No Known Activations