INDEX

Explanations

content from forum posts, introductions and people getting to know each other

oai_token-act-pair · gemini-2.0-flash

Direct address, age, turns

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 acquaintance

-0.63

 xenia

-0.56

 purpoſe

-0.54

 getenv

-0.54

Efq

-0.53

 stranger

-0.51

 acquainted

-0.48

 poffible

-0.48

 opaque

-0.47

 آشنا

-0.47

POSITIVE LOGITS

ConstraintMaker

0.72

LookAnd

0.71

 للمعارف

0.70

 שוליים

0.68

 ModelExpression

0.67

 通販

0.66

MemoryWarning

0.60

IsMutable

0.59

 INTERESAR

0.58

::$_

0.58

Activations Density 19.556%

content from forum posts, introductions and people getting to know each other

Direct address, age, turns

No Comments

No Known Activations