INDEX

Explanations

the word "said" or "began" followed by "on"

oai_token-act-pair · gemini-2.0-flash

on

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

expandindo

-0.77

ConstraintMaker

-0.70

IntoConstraints

-0.67

 فريبيس

-0.66

 utafitiHapana

-0.65

 ويكيپيديا

-0.63

 ویکی‌پدیای

-0.60

URLException

-0.59

قایناقلار

-0.59

spesies

-0.59

POSITIVE LOGITS

ON

0.49

on

0.48

onde

0.48

<bos>

0.47

onne

0.46

 defaultstate

0.45

 Simon

0.45

cag

0.44

Document

0.42

Lew

0.42

Activations Density 1.255%

the word "said" or "began" followed by "on"

on

No Comments

No Known Activations