INDEX

Explanations

conditional phrases indicating potential outcomes or risks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

GEBURTSDATUM

-1.02

 Administrativna

-0.90

 propOrder

-0.89

Obrázky

-0.88

ThroughAttribute

-0.88

 ModelRenderer

-0.78

OGND

-0.78

 resourceCulture

-0.78

ollectionView

-0.77

Personensuche

-0.77

POSITIVE LOGITS

 often

0.83

 sometimes

0.82

 also

0.79

 oftentimes

0.79

 Sometimes

0.77

 potentially

0.76

 Often

0.74

Often

0.72

 typically

0.71

 menudo

0.71

Activations Density 0.316%

conditional phrases indicating potential outcomes or risks

No Comments

No Known Activations