INDEX

Explanations

terms related to elected positions and officials

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

yntaxException

-0.98

 ujednoznacz

-0.83

TintMode

-0.79

EndContext

-0.79

/*

-0.79

fillType

-0.78

 مشين

-0.75

OrBuilder

-0.74

rrggbb

-0.73

 Warehouse

-0.72

POSITIVE LOGITS

 elected

2.61

 Elected

2.16

elected

1.99

 elect

1.69

 ELECT

1.49

 electing

1.49

Elect

1.37

 élu

1.35

 Elect

1.33

 élus

1.16

Activations Density 0.094%

terms related to elected positions and officials

No Comments

No Known Activations