INDEX

Explanations

instances of one person being acted upon by another

oai_token-act-pair · gemini-2.0-flash

upside

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

lccn

-0.58

EndProject

-0.53

 their

-0.52

اریخ

-0.50

Carriera

-0.50

gain

-0.46

 ihren

-0.46

ern

-0.46

ndez

-0.45

jon

-0.45

POSITIVE LOGITS

^(@)

0.65

 CreateTagHelper

0.65

 يتيمه

0.63

hastly

0.60

 متعلقه

0.60

ituaries

0.57

今度は

0.57

 rarer

0.57

 تضيفلها

0.56

antiate

0.55

Activations Density 1.833%

instances of one person being acted upon by another

upside

No Known Activations