INDEX

Explanations

phrases indicating relationships, dependencies, and actions taken by individuals or groups

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

kloped

-0.44

Хьажоргаш

-0.44

umo

-0.44

omar

-0.43

/*-

-0.41

umoj

-0.40

WindowConstants

-0.40

oped

-0.40

sev

-0.40

出版年

-0.39

POSITIVE LOGITS

him

0.60

 honom

0.46

 kepad

0.42

kelijke

0.39

addSubview

0.39

 الرياضيه

0.38

 addSubview

0.36

tauscht

0.35

 viņ

0.35

 Médico

0.35

Activations Density 0.521%

phrases indicating relationships, dependencies, and actions taken by individuals or groups

No Comments

No Known Activations