INDEX

Explanations

dead

np_token-act-pair-logits · gemini-2.0-flash

words that are negative in tone or themes related to those who cannot see

oai_token-act-pair · gemini-2.0-flash

dead/blind

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

\{\\

-0.82

ViewFeatures

-0.73

 autorytatywna

-0.69

таратура

-0.67

CloseOperation

-0.65

 FetchType

-0.64

MigrationBuilder

-0.62

NameInMap

-0.62

 محفوظة

-0.60

tagHelperRunner

-0.60

POSITIVE LOGITS

orphic

0.44

spot

0.43

 files

0.42

 person

0.41

 bones

0.41

File

0.41

árl

0.40

doj

0.40

est

0.39

files

0.39

Activations Density 1.383%

dead

words that are negative in tone or themes related to those who cannot see

dead/blind

No Comments

No Known Activations