INDEX

Explanations

question words such as "why" and "¿Por"

oai_token-act-pair · gemini-2.0-flash

asking "why"

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

why

-1.02

 waarom

-1.00

 chi̍t

-0.91

why

-0.88

 Зачем

-0.83

Why

-0.82

 pourquoi

-0.82

Why

-0.82

 Waarom

-0.81

WHY

-0.80

POSITIVE LOGITS

 صوتيه

0.59

arraycopy

0.55

schild

0.54

 متحده

0.52

XmlType

0.50

indere

0.49

ModelAdmin

0.49

IBarButtonItem

0.47

ourage

0.46

 AppCompatTheme

0.46

Activations Density 5.175%

question words such as "why" and "¿Por"

asking "why"

No Comments

No Known Activations