INDEX

Explanations

specific nouns and proper nouns relevant to various subjects, including names, places, and items

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.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

GEBURTSDATUM

-1.17

 <>",

-1.01

rungsseite

-1.00

 <=",

-0.94

errHandler

-0.94

MessageTagHelper

-0.92

bewerken

-0.91

 المعيارى

-0.88

 otomatig

-0.87

SourceChecksum

-0.87

POSITIVE LOGITS

<eos>

0.51

0.50

0.48

0.47

ge

0.46

 orang

0.45

top

0.45

top

0.44

↵↵

0.43

Ge

0.43

Activations Density 0.013%

specific nouns and proper nouns relevant to various subjects, including names, places, and items

No Comments

No Known Activations