INDEX

Explanations

references to families and relationships, especially those of men and their children

oai_token-act-pair · gemini-2.0-flash

his

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Exacts

-0.55

ValueGeneration

-0.53

Clik

-0.50

 שוליים

-0.48

${

-0.48

Datuak

-0.46

Dis

-0.43

κτηρισ

-0.43

 eksemp

-0.43

oquia

-0.42

POSITIVE LOGITS

VersionUID

0.68

 myſelf

0.62

 raiſ

0.61

 themſelves

0.59

Efq

0.59

PRWEB

0.58

 himſelf

0.58

 estimés

0.57

exitRule

0.56

ilibrium

0.56

Activations Density 2.691%

references to families and relationships, especially those of men and their children

his

No Comments

No Known Activations