INDEX

Explanations

angle bracket enclosed XML tags and seemingly random code snippets

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

tagHelperRunner

-0.75

AndEndTag

-0.59

assertRaises

-0.46

 MainAxisSize

-0.44

 hany

-0.44

 المعيارى

-0.41

kny

-0.41

rzost

-0.40

DockStyle

-0.40

reactivex

-0.40

POSITIVE LOGITS

ThroughAttribute

0.75

aarrggbb

0.63

 &___

0.59

EndGlobalSection

0.57

CloseOperation

0.56

NameInMap

0.56

 validamos

0.55

 Normdatei

0.55

 udaler

0.55

 Reichstag

0.55

Activations Density 1.168%

angle bracket enclosed XML tags and seemingly random code snippets

code

No Comments

No Known Activations