INDEX

Explanations

family history and genealogical information, especially with personal pronouns

oai_token-act-pair · gemini-2.0-flash

terms related to genetics and family ancestry

np_token-act-pair-logits · gpt-4o-mini

genes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onAnimation

-0.67

клопе

-0.62

 дописавши

-0.60

 MonoBehaviour

-0.55

StoryboardSegue

-0.49

 censiti

-0.48

 distanciation

-0.47

).]

-0.46

 doInBackground

-0.46

 rematch

-0.45

POSITIVE LOGITS

 gene

0.71

 genes

0.63

genes

0.59

 Family

0.59

GENE

0.58

Family

0.57

Gene

0.57

 Gene

0.56

gene

0.56

 Genes

0.54

Activations Density 3.041%

family history and genealogical information, especially with personal pronouns

terms related to genetics and family ancestry

genes

No Comments

No Known Activations