INDEX

Explanations

words that are part of a philosophical discussion

oai_token-act-pair · gemini-2.0-flash

Literature and philosophy texts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 चीज़ों

-0.45

最快更新

-0.44

 cosy

-0.43

ẵn

-0.42

TypedDataSet

-0.40

"]/

-0.38

httphttps

-0.37

cista

-0.37

MethodManager

-0.37

 onAnimation

-0.37

POSITIVE LOGITS

parsedMessage

0.73

ExtendWith

0.69

 Normdatei

0.69

xase

0.65

 ویکی‌پدیا

0.61

uxxxx

0.60

 esternos

0.59

wieś

0.59

ophores

0.59

 Bureau

0.57

Activations Density 4.905%

words that are part of a philosophical discussion

Literature and philosophy texts

No Comments

No Known Activations