INDEX

Explanations

proper nouns or names with capitalization

oai_token-act-pair · gemini-2.0-flash

Chat logs

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

 Diſ

-0.78

 Reſ

-0.77

 Perſ

-0.73

neſs

-0.70

 Conſ

-0.70

 itſelf

-0.69

 Chriftian

-0.68

 Inſ

-0.68

 pleaſure

-0.67

 ſhe

-0.66

POSITIVE LOGITS

 Roskov

0.62

ArgsConstructor

0.55

Frankreich

0.52

GIVEREF

0.52

0.49

ண்டும்

0.49

0.48

Tikang

0.48

__).

0.48

Activations Density 1.038%

proper nouns or names with capitalization

Chat logs

No Comments

No Known Activations