INDEX

Explanations

words related to events that happened during a specific time period or era

oai_token-act-pair · gemini-2.0-flash

something has ended

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

ArrowToggle

-0.59

Personensuche

-0.56

Portale

-0.52

χος

-0.50

бият

-0.48

🔕

-0.47

estacks

-0.47

awarkan

-0.46

partida

-0.46

 vétérina

-0.46

POSITIVE LOGITS

 ended

1.39

 ends

1.38

 continued

1.23

 lasted

1.22

 continues

1.20

 Ends

1.16

 continue

1.09

Ends

1.04

ended

1.03

 lasts

1.03

Activations Density 1.845%

words related to events that happened during a specific time period or era

something has ended

No Comments

No Known Activations