INDEX

Explanations

references to specific categories, particularly related to definitions, attributes, and instances involving elements or 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

 referrerpolicy

-0.65

erdings

-0.56

MENAFN

-0.56

}^{+}$

-0.49

urts

-0.48

 cláus

-0.46

 Pons

-0.46

 Ababa

-0.46

 perd

-0.45

diens

-0.45

POSITIVE LOGITS

EDEFAULT

0.83

 تضيفلها

0.80

 disambiguazione

0.74

 CreateTagHelper

0.71

verwijspagina

0.70

thâu

0.68

@[+][

0.66

 ujednoznacz

0.65

таратура

0.61

 isInitialized

0.60

Activations Density 0.917%

references to specific categories, particularly related to definitions, attributes, and instances involving elements or concepts

No Comments

No Known Activations