INDEX

Explanations

lists of people and topics in a podcast or show

oai_token-act-pair · gemini-2.0-flash

podcast episodes

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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

expandindo

-0.77

:✨

-0.70

 AssemblyCulture

-0.69



-0.68

 بيها

-0.64

 otomatig

-0.63

 MainAxisSize

-0.63

AndEndTag

-0.63

 AssemblyCompany

-0.61

AutoScaleMode

-0.59

POSITIVE LOGITS

 episode

1.36

 podcast

1.29

Podcast

1.16

 Episode

1.14

 episodes

1.13

episode

1.13

Pod

1.13

pod

1.13

pod

1.13

Episode

1.08

Activations Density 0.554%

lists of people and topics in a podcast or show

podcast episodes

No Comments

No Known Activations