INDEX

Explanations

first person references alongside auxiliary and modal verbs

oai_token-act-pair · gemini-2.0-flash

am/m

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 ExecuteAsync

-0.94

Geplaatst

-0.71

 ProtoMessage

-0.67

InstrumentedTest

-0.66

ReusableCell

-0.66

ValueGeneration

-0.65

ValueStyle

-0.63

 veckor

-0.61

XMLSchema

-0.61

 trajets

-0.60

POSITIVE LOGITS

 attempting

0.58

 trying

0.58

 unable

0.57

 able

0.56

 dealing

0.55

 doing

0.51

如何

0.50

 ogóle

0.49

 using

0.48

ittäin

0.44

Activations Density 1.914%

first person references alongside auxiliary and modal verbs

am/m

No Comments

No Known Activations