INDEX

Explanations

terms and phrases related to polarity and polarized states in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 Hewitt

-0.47

 Kenney

-0.47

expandindo

-0.45

 Harwood

-0.45

 duque

-0.44

Merci

-0.43

 برانيه

-0.43

Museum

-0.43

 Üniversitesi

-0.41

 Mancha

-0.40

POSITIVE LOGITS

 Polar

1.09

 polar

1.08

polar

1.07

Polar

1.00

ipolar

0.92

 polarity

0.73

 Polaris

0.69

 bipolar

0.66

 polarization

0.65

 Polarization

0.62

Activations Density 0.009%

terms and phrases related to polarity and polarized states in various contexts

No Comments

No Known Activations