INDEX

Explanations

references to computers or computer systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 يتيمه

-0.68

:✨

-0.67

kirche

-0.55

 INTERESAR

-0.54

 Herman

-0.53

erialize

-0.52

FXMLLoader

-0.52

lom

-0.49

RESUMO

-0.49

HasIndex

-0.48

POSITIVE LOGITS

fromnode

0.73

 homenaje

0.70

']],

0.66

 onAnimation

0.66

'])

0.64

 Klee

0.62

 computers

0.62

)]=

0.61

 Krie

0.61

']]

0.60

Activations Density 0.242%

references to computers or computer systems

No Comments

No Known Activations