INDEX

Explanations

references to figures in a scientific paper, particularly those with overlaid lines, arrows, and legends

oai_token-act-pair · gemini-2.0-flash

diagrams and plots

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Glance

-0.60

doodle

-0.58

rivial

-0.57

Datuak

-0.55

 Icons

-0.54

</tfoot>

-0.54

 arrows

-0.53

ddots

-0.53

 thuận

-0.52

 Ripper

-0.52

POSITIVE LOGITS

RegressionTest

0.66

MemoryWarning

0.56

 full

0.51

存于互联网档案馆

0.50

 noDo

0.48

 Full

0.48

 AssemblyProduct

0.47

/**

0.47

 redor

0.47

⟭

0.45

Activations Density 4.878%

references to figures in a scientific paper, particularly those with overlaid lines, arrows, and legends

diagrams and plots

No Comments

No Known Activations