INDEX

Explanations

the terminology and symbols of scientific writing

oai_token-act-pair · gemini-2.0-flash

roots related to 'particle'

np_token-act-pair-logits · gpt-4o-mini

CMB lensing signal processing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArrowToggle

-0.95

出版年

-0.90

 "..\..\

-0.87

 gynhyrchwyd

-0.86

ItemBackground

-0.85

 resourceCulture

-0.84

 estimés

-0.84

 itſelf

-0.81

IntoConstraints

-0.80

ftagPool

-0.79

POSITIVE LOGITS

par

0.56

ul

0.46

Par

0.45

ar

0.44

0.42

par

0.41

])).

0.40

 semi

0.40

0.39

0.38

Activations Density 3.132%

the terminology and symbols of scientific writing

roots related to 'particle'

CMB lensing signal processing

No Comments

No Known Activations