INDEX

Explanations

words relating to medical interventions and medication for various conditions

oai_token-act-pair · gemini-2.0-flash

terms related to access and resources

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

Health and medicine

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Villages

-0.52

 villages

-0.48

 upgra

-0.48

 mosques

-0.45

 knuckles

-0.45

 concub

-0.45

 dikes

-0.44

glises

-0.42

 lodges

-0.42

 Lisbon

-0.42

POSITIVE LOGITS

 resourceCulture

0.83

NameInMap

0.81

 access

0.76

 famí

0.70

 Access

0.70

IBarButtonItem

0.68

Access

0.67

Personendaten

0.66

webElement

0.66

Geplaatst

0.66

Activations Density 3.306%

words relating to medical interventions and medication for various conditions

terms related to access and resources

Health and medicine

No Comments

No Known Activations