INDEX

Explanations

expressions of speech or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 препратки

-0.60

tableFuture

-0.49

 estekak

-0.45

 خارجية

-0.44

[]*

-0.44

ंदीखरीदारी

-0.43

 ujednoznacz

-0.43

 locality

-0.42

 disambiguazione

-0.41

POSITIVE LOGITS

 сказать

0.62

say

0.57

UnusedPrivate

0.57

 decir

0.54

 скажу

0.45

 pensez

0.45

 speak

0.44

AccessorTable

0.43

 powiedzieć

0.43

?>

0.42

Activations Density 0.056%

expressions of speech or dialogue

No Comments

No Known Activations