INDEX

Explanations

terms related to neutrons or neutron-related concepts in the text

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 producteurs

-0.91

 ritrov

-0.86

 bénéfices

-0.83

 Wither

-0.82

 BioLib

-0.81

pexpr

-0.80

Vezi

-0.80

 Clarissa

-0.79

 للاسماء

-0.79

 producteur

-0.78

POSITIVE LOGITS

 neutron

1.59

neutron

1.44

Neutron

1.40

 Neutron

1.33

 neutrons

1.32

trons

0.85

Datuak

0.68

 Woolf

0.62

es

0.58

 alto

0.56

Activations Density 0.001%

terms related to neutrons or neutron-related concepts in the text

No Comments

No Known Activations