INDEX

Explanations

specific names and terms related to diet, religious affiliations, and certain statistical or mathematical concepts

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

✨:

-0.85

helves

-0.71

Cordialement

-0.70

ilingual

-0.69

 האם

-0.68

สือ

-0.65

 geschlagen

-0.65

 sauvages

-0.64

 inoxydable

-0.64

 hvem

-0.62

POSITIVE LOGITS

Rhestr

0.73

ंदीखरीदारी

0.71

 Ressource

0.68

 Gang

0.66

HAB

0.66

dAtA

0.65

 tibet

0.65

 Omen

0.65

تها

0.65

Réalisation

0.65

Activations Density 0.439%

specific names and terms related to diet, religious affiliations, and certain statistical or mathematical concepts

No Comments

No Known Activations