INDEX

Explanations

proper nouns associated with specific individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

󠁣

-0.49



-0.48

󠁮

-0.47

ⓧ

-0.47

İstinadlar

-0.46

település

-0.46

anglès

-0.45

𝟹

-0.45

gridy

-0.45

Życiorys

-0.45

POSITIVE LOGITS

\{\\

0.62

XmlAccessType

0.54

0.38

PropertyChanging

0.38

 mergeFrom

0.38

 Evansville

0.37

0.35

 Maschine

0.35

 jsonData

0.35

 essi

0.34

Activations Density 0.806%

proper nouns associated with specific individuals or entities

No Comments

No Known Activations