INDEX

Explanations

phrases related to improving health and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

pesas

-0.49

DockStyle

-0.48

Berna

-0.45

SequentialGroup

-0.44

}{*}{}

-0.44

 HasFactory

-0.42

radius

-0.42

VARCHAR

-0.42

⟬

-0.41

 apellidos

-0.41

POSITIVE LOGITS

 quality

0.91

 efficiencies

0.87

 efficiency

0.85

 readability

0.79

quality

0.79

efficiency

0.77

 InputDecoration

0.77

 qualité

0.77

Quality

0.76

 Quality

0.76

Activations Density 0.126%

phrases related to improving health and well-being

No Comments

No Known Activations