INDEX

Explanations

references to academic papers by recognizing patterns of numbers representing years of publication

oai_token-act-pair · gemini-2.0-flash

say comma

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

providedIn

-0.74

 snippetHide

-0.73

ues

-0.66

ftagPool

-0.59

GroupLayout

-0.56

UES

-0.55

fjspx

-0.55

InjectMocks

-0.53

ULO

-0.52

Datuak

-0.51

POSITIVE LOGITS

 InputDecoration

0.67

Personendaten

0.63

 ffilmiau

0.56

 isInitialized

0.55

extAlignment

0.54

дарю

0.50

 estekak

0.49

contentLoaded

0.46

Kjelder

0.45

andoah

0.44

Activations Density 2.738%

references to academic papers by recognizing patterns of numbers representing years of publication

say comma

No Comments

No Known Activations