INDEX

Explanations

mentions of the name "David" followed by another word

oai_token-act-pair · gemini-2.0-flash

David

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 internasional

-0.40

 raggiung

-0.39

方

-0.39

 offent

-0.38

 fundido

-0.37

 lumea

-0.37

 perang

-0.37

řízen

-0.37

 that

-0.36

POSITIVE LOGITS

 للمعارف

1.02

IndentedString

0.97

 متعلقه

0.92

Autoritní

0.92

SharedCtor

0.91

 Roskov

0.90

extAlignment

0.89

 iNdEx

0.89

rungsseite

0.88

RTEE

0.86

Activations Density 0.315%

mentions of the name "David" followed by another word

David

No Comments

No Known Activations