INDEX

Explanations

phrases indicating research support and funding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Dried

-0.59

dried

-0.59

 createState

-0.58

]--;

-0.57

 dried

-0.55

 Dried

-0.54

LEncoder

-0.54

 lost

-0.54

ValueGenerated

-0.54

 missed

-0.51

POSITIVE LOGITS

 aided

1.80

 accompanied

1.78

 fueled

1.64

 assisted

1.62

 supported

1.61

 accompagné

1.57

 backed

1.55

 fuelled

1.50

 acompañado

1.48

 Supported

1.46

Activations Density 0.198%

phrases indicating research support and funding

No Comments

No Known Activations