INDEX

Explanations

references to specific individuals and their familial or occupational titles

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

first and last names

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 podjela

-0.48

󠁴

-0.45

 przeci

-0.41

 ferons

-0.40

 Salter

-0.40

 لئے

-0.39

 substantially

-0.38

 uVar

-0.38

 hemos

-0.38

 Italijani

-0.37

POSITIVE LOGITS

ANTLR

0.56

awaiter

0.50

expandindo

0.49

 Anſ

0.48

AddTagHelper

0.47

yyr

0.46

ğren

0.46

下载附件

0.46

endphp

0.45

 Désolé

0.45

Activations Density 0.009%

references to specific individuals and their familial or occupational titles

first and last names

No Comments

No Known Activations