INDEX

Explanations

positive reactions by groups of people as well as learning environments and events

oai_token-act-pair · gemini-2.0-flash

applause

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 enfans

-0.57

expandindo

-0.54

 tasca

-0.48

 sélectionnez

-0.48

 refroid

-0.48

ministrazione

-0.48

ViewFeatures

-0.47

 Majefty

-0.47

 accepté

-0.47

örs

-0.47

POSITIVE LOGITS

 applause

0.81

 Clap

0.79

Applause

0.79

PerformLayout

0.75

 appla

0.74

 applaud

0.73

 standing

0.72

 clap

0.71

forChild

0.68

Apre

0.67

Activations Density 0.727%

positive reactions by groups of people as well as learning environments and events

applause

No Comments

No Known Activations