INDEX

Explanations

words and phrases related to charitable giving, helping, and volunteering

oai_token-act-pair · gemini-2.0-flash

charitable causes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

<bos>

-0.91

 volunteer

-0.57

してくれる

-0.51

 donations

-0.49

 donation

-0.47

 Donations

-0.47

laga

-0.41

 сбо

-0.41

Donations

-0.41

patreon

-0.41

POSITIVE LOGITS

 Wund

0.72

 للاسماء

0.71

μφωνα

0.69

 ͡°

0.69

клопе

0.67

 Samaria

0.67

AndEndTag

0.67

 Charlemagne

0.66

 Biographie

0.65

DispatchToProps

0.65

Activations Density 2.225%

words and phrases related to charitable giving, helping, and volunteering

charitable causes

No Comments

No Known Activations