INDEX

Explanations

proper nouns, especially names

oai_token-act-pair · 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

 individual

-0.48

-0.46

قليم

-0.45

com

-0.44

 like

-0.39

pen

-0.38

 contact

-0.37

كويكب

-0.36

вари

-0.36

unter

-0.36

POSITIVE LOGITS

 الحره

0.75

rrggbb

0.71

Parcelize

0.69

 apporté

0.68

TemporalType

0.68

berdayakan

0.66

PullParser

0.65

 RIPRODUZIONE

0.65

Rhestr

0.65

tagHelperRunner

0.63

Activations Density 2.604%

proper nouns, especially names

No Comments

No Known Activations