INDEX

Explanations

proper nouns, specifically names of people

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

enterOuterAlt

-0.45

 habet

-0.41

pēc

-0.39

 noastre

-0.38

OGND

-0.37

 attivo

-0.34

 isolato

-0.34

zeigt

-0.33

Trọng

-0.33

/**

-0.33

POSITIVE LOGITS

 GenerationType

0.63

findpost

0.54

canestro

0.50

ismet

0.49

 continúas

0.49

ьаж

0.49

➟

0.48

الحياه

0.47

DOCTYPE

0.47

doctype

0.47

Activations Density 0.041%

proper nouns, specifically names of people

No Comments

No Known Activations