INDEX

Explanations

references to scientific or medical terms and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

uxxxx

-0.54

PYX

-0.48

 raggiunto

-0.42

 stanovnika

-0.41

гни

-0.40

Архівовано

-0.40

netbeans

-0.39

masin

-0.39

们

-0.38

encodeWith

-0.37

POSITIVE LOGITS

 itſelf

0.81

 Monfieur

0.73

 myſelf

0.71

ſelves

0.66

 विश्वसनीयता

0.66

IsContent

0.65

 Reſ

0.64

 ſhe

0.64

 consultato

0.63

 poffe

0.63

Activations Density 0.776%

references to scientific or medical terms and conditions

No Comments

No Known Activations