INDEX

Explanations

references to the name 'Mur' in various forms and contexts

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

 Kitts

-0.84

 Fins

-0.77

Britt

-0.76

Haf

-0.74

 Elizabethan

-0.74

 ſmall

-0.74

Dax

-0.73

Gs

-0.73

 ſen

-0.72

XG

-0.71

POSITIVE LOGITS

Mur

1.85

Mur

1.63

mur

1.55

mur

1.41

 Murdoch

1.41

MUR

1.40

 Murray

1.39

 Murat

1.37

MUR

1.35

 Murdock

1.23

Activations Density 0.014%

references to the name 'Mur' in various forms and contexts

No Comments

No Known Activations