INDEX

Explanations

references to individuals and their roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Praze

-0.32

 sektor

-0.30

 dále

-0.30

 recorrido

-0.29

 sistem

-0.29

">—

-0.28

 traseiro

-0.27

 infrastruktur

-0.27

 terbuka

-0.27

 hodiny

-0.26

POSITIVE LOGITS



0.77

SharedDtor

0.76

contentLoaded

0.68

 ujednoznacz

0.67

 PeEnEo

0.65

<unused74>

0.63

<unused14>

0.63

<unused52>

0.63

<unused3>

0.63

<unused8>

0.63

Activations Density 0.796%

references to individuals and their roles in various contexts

No Comments

No Known Activations