INDEX

Explanations

code artifacts containing dates, especially date information associated with code creation

oai_token-act-pair · gemini-2.0-flash

code, logs, dates/times

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bootstrapcdn

-0.72

دانشنامهٔ

-0.69

 nahilalakip

-0.67

̍t

-0.60

CppMethod

-0.60

Revenir

-0.56

Datuak

-0.56

EndContext

-0.56

исленность

-0.54

 transfieras

-0.54

POSITIVE LOGITS

 âgées

0.58

 defaultstate

0.56

 hemsida

0.49

 keduanya

0.49

 sélectionnés

0.48

 geworden

0.48

 řízení

0.48

 Reproduce

0.48

 endroits

0.46

 ProtoMessage

0.46

Activations Density 0.260%

code artifacts containing dates, especially date information associated with code creation

code, logs, dates/times

No Comments

No Known Activations