INDEX

Explanations

terms associated with craniofacial features and conditions

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

 المعيارى

-0.90

 nahilalakip

-0.82

Bett

-0.74

 fören

-0.73

 Lowry

-0.72

toPromise

-0.68

 scurt

-0.66

 buurt

-0.66

 Sert

-0.65

chl

-0.65

POSITIVE LOGITS

 Cran

1.48

Cran

1.36

 cran

1.30

cran

1.16

cranial

1.09

 cranial

1.09

 Skull

0.96

 skull

0.91

skull

0.90

 kran

0.87

Activations Density 0.004%

terms associated with craniofacial features and conditions

No Comments

No Known Activations