INDEX

Explanations

references to specific geographical locations or names

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

@"/

-0.44

-0.43

 comp

-0.43

kehr

-0.39

Solicit

-0.37

Кли

-0.37

cheibe

-0.36

 اع

-0.36

 vær

-0.35

Recipient

-0.34

POSITIVE LOGITS

 Cole

0.67

GOTREF

0.66

SpringBootTest

0.60

 COLE

0.60

Cole

0.57

NOPQRST

0.57

bearded

0.57

Демографія

0.56

tagext

0.55

wool

0.54

Activations Density 0.286%

references to specific geographical locations or names

No Known Activations