INDEX

Explanations

sections of text that contain numerical data or units of measurement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IVEREF

-0.82

SourceChecksum

-0.79

bootstrapcdn

-0.75

+#+

-0.72

GEBURTSDATUM

-0.72

Personendaten

-0.71

 transférez

-0.70

ariConfig

-0.70

SOUNDBITE

-0.70

 AssemblyProduct

-0.69

POSITIVE LOGITS

InjectAttribute

1.50

gdx

0.53

ceae

0.50

expandindo

0.50

boxer

0.49

 nakalista

0.49

HOUT

0.49

 bénéfices

0.47

 carottes

0.47

Referencias

0.46

Activations Density 0.005%

sections of text that contain numerical data or units of measurement

No Comments

No Known Activations