INDEX

Explanations

sentences that talk about how something happens or is done.

oai_token-act-pair · gemini-2.0-flash

explains behavior with "way"

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

Not in Any Lists

No Comments

Negative Logits

Atsauces

-0.57

 REPUBLIC

-0.53

<bos>

-0.51

DataMember

-0.49

PlaceHolder

-0.47

гинал

-0.46

searched

-0.46

/******/

-0.46

ģ

-0.45

envol

-0.45

POSITIVE LOGITS

 Shakspeare

0.77

IBarButtonItem

0.70

intios

0.69

 Monfieur

0.68

setVerticalGroup

0.67

 initComponents

0.64

ItemBackground

0.63

EDEFAULT

0.62

 defaultstate

0.62

 snippetHide

0.60

Activations Density 1.274%

sentences that talk about how something happens or is done.

explains behavior with "way"

No Comments

No Known Activations