INDEX

Explanations

references to specific entities and events in narrative or informational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

@"/

-0.57

aarrggbb

-0.48

 comuniques

-0.48

inheritDoc

-0.48

ylvan

-0.47

 honor

-0.46

تقاوى

-0.46

AndEndTag

-0.45

Erstellt

-0.45

ErrUnexpectedEOF

-0.44

POSITIVE LOGITS

GEBURTSDATUM

0.48

migrationBuilder

0.46

 &___

0.45

 intérieure

0.44

 extérieure

0.41

 sidang

0.39

 sicherzustellen

0.38

 gravidanza

0.38

 znaj

0.37

 peito

0.37

Activations Density 0.870%

references to specific entities and events in narrative or informational contexts

No Comments

No Known Activations