INDEX

Explanations

words related to research and health risks

oai_token-act-pair · gemini-2.0-flash

Research studies

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.65

)++;

-0.60

 withal

-0.57

 dépens

-0.57

 متعلقه

-0.54

 récompense

-0.53

vesi

-0.53

المصدر

-0.52

posób

-0.51

 clearness

-0.51

POSITIVE LOGITS

Rohy

0.67

ModelSerializer

0.58

 CreateTagHelper

0.55

<bos>

0.54

ReusableCell

0.54

>//

0.51

styleType

0.49

 Wikimedijinoj

0.48

StatusOK

0.45

jooq

0.44

Activations Density 1.399%

words related to research and health risks

Research studies

No Comments

No Known Activations