INDEX

Explanations

references to lymphocytes

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

 resourceCulture

-0.81

IsContent

-0.80

OCCURRED

-0.75

تقاوى

-0.68

Aholisi

-0.66

 ujednoznacz

-0.65

istoitu

-0.65

ariConfig

-0.64

 вікі

-0.63

intios

-0.61

POSITIVE LOGITS

 lymphocytes

1.26

 lymphocyte

1.09

 Lympho

1.04

 lympho

0.93

Wro

0.78

 Abbé

0.74

 Alegre

0.71

 privés

0.69

 subprocess

0.68

 שוליים

0.68

Activations Density 0.003%

references to lymphocytes

No Comments

No Known Activations