INDEX

Explanations

words that introduce lists or provide examples

oai_token-act-pair · gemini-2.0-flash

Lists and indexes

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

includes

-0.60

MigrationBuilder

-0.60

 Италијани

-0.57

ValueStyle

-0.57

useState

-0.56

 ReactDOM

-0.54

Includes

-0.52

flink

-0.50

 Lainnya

-0.49

 Egon

-0.48

POSITIVE LOGITS

раздо

0.68

 архивлан

0.60

OGND

0.55

Digitized

0.55

 pageContext

0.53

Solución

0.52

adə

0.51

 numerus

0.50

 CLERK

0.49

 judicia

0.48

Activations Density 0.640%

words that introduce lists or provide examples

Lists and indexes

No Comments

No Known Activations