INDEX

Explanations

pronouns used in the context of being at a location

oai_token-act-pair · gemini-2.0-flash

diary entries

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

onViewCreated

-0.84

 kasarigan

-0.77

\{\\

-0.77

queryInterface

-0.75

MemoryWarning

-0.73

LookAnd

-0.73

 ModelExpression

-0.71

لينكات

-0.68

 مرئيه

-0.66

AxisAlignment

-0.64

POSITIVE LOGITS

 contentType

0.52

OrUpdate

0.48

ὶ

0.47

DTM

0.46

 aveug

0.46

Propag

0.43

airport

0.42

glGen

0.42

Пор

0.41

moins

0.41

Activations Density 1.606%

pronouns used in the context of being at a location

diary entries

No Comments

No Known Activations