INDEX

Explanations

emotionally charged language

oai_token-act-pair · gemini-2.0-flash

profanity and exclamations

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

Profanity

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

 GenerationType

-0.79

OGND

-0.71

 ModelExpression

-0.69

+#+#

-0.67

ècie

-0.66

下载附件

-0.66

ніципалі

-0.64

цездатний

-0.64

 חיצוניים

-0.63

GEBURTSDATUM

-0.63

POSITIVE LOGITS

tf

0.71

ass

0.62

god

0.56

god

0.53

TF

0.52

 diab

0.52

tf

0.51

ass

0.51

 Fucking

0.46

asf

0.46

Activations Density 0.892%

emotionally charged language

profanity and exclamations

Profanity

No Comments

No Known Activations