INDEX

Explanations

structured phrases that emphasize features or capabilities

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_131k/average_l0_101

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

parsedMessage

-0.56

ValueStyle

-0.52

sup

-0.48

ImageContext

-0.48

хьтан

-0.44

 Sehr

-0.44

createNewFile

-0.43

 trou

-0.43

 يتيمه

-0.43

GOTREF

-0.43

POSITIVE LOGITS

 geçir

0.43

 trovar

0.43

 dukungan

0.41

 Mischung

0.40

 jutaan

0.40

 Paglinawan

0.40

จบ

0.40

 kartun

0.39

 ruangan

0.38

 zís

0.38

Activations Density 0.010%

structured phrases that emphasize features or capabilities

No Comments

No Known Activations