INDEX

Explanations

terms associated with nominal values and statistical measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits



-0.89

 CommonModule

-0.87

 houſe

-0.86

 Monfieur

-0.84

 Соб

-0.79

ViewFeatures

-0.78

Odon

-0.78

Eſ

-0.77

 purpoſe

-0.77

❤❤

-0.76

POSITIVE LOGITS

 Cruz

0.83

 Claw

0.82

 Benzema

0.78

 SWIG

0.76

 Blazers

0.74

maid

0.73

Claw

0.73

 McGrath

0.73

alyptus

0.73

 Hoss

0.72

Activations Density 1.598%

terms associated with nominal values and statistical measures

No Comments

No Known Activations