INDEX

Explanations

occurrence of the word "up"

oai_token-act-pair · gemini-2.0-flash

up

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

bewerken

-0.85

SourceChecksum

-0.76

 auroit

-0.70

 StatefulWidget

-0.69

 Савезне

-0.69

 myſelf

-0.68

 feroit

-0.68

UpdateCommand

-0.68

 pleaſure

-0.68

featureID

-0.67

POSITIVE LOGITS

tokenize

0.55

Bre

0.52

Mil

0.49

channel

0.46

cy

0.45

Ass

0.45

 FetchType

0.45

 there

0.44

providedIn

0.44

API

0.43

Activations Density 0.471%

occurrence of the word "up"

up

No Comments

No Known Activations