INDEX

Explanations

terms related to awards and recognition events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 saites

-0.77

NameInMap

-0.74

})->

-0.69

 ujednoznacz

-0.68

 AttributeSet

-0.67

 ExecuteAsync

-0.66

GOTREF

-0.65

AccessorTable

-0.64

óngase

-0.62

LabelTagHelper

-0.62

POSITIVE LOGITS

 potenza

0.55

kega

0.53

th

0.50

InBackground

0.50

ViewImports

0.49

VI

0.49

 dictadura

0.48

 sixth

0.47

 vectoriales

0.47

 edition

0.47

Activations Density 0.510%

terms related to awards and recognition events

No Comments

No Known Activations