INDEX

Explanations

words related to complexity, difficulty, and breaking apart

oai_token-act-pair · gemini-2.0-flash

already

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

WithIOException

-0.62

eaways

-0.62

AdapterFactory

-0.61

initializeApp

-0.60

Gambas

-0.60

HtmlAttribute

-0.55

SEVERE

-0.53

CppCodeGen

-0.49

ionView

-0.49

 Roskov

-0.49

POSITIVE LOGITS

 already

3.55

already

3.27

 Already

3.09

Already

3.00

 ALREADY

2.77

 allerede

2.25

 déjà

2.19

 redan

2.16

 già

2.11

 уже

2.06

Activations Density 1.667%

words related to complexity, difficulty, and breaking apart

already

No Comments

No Known Activations