INDEX

Explanations

proper nouns, specifically related to places and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/**

-0.55

SpringBootTest

-0.55

DotNetBar

-0.54

 present

-0.53

 разделе

-0.51

Források

-0.48

#!/

-0.47

 North

-0.46

BMP

-0.46

minente

-0.45

POSITIVE LOGITS

RegressionTest

0.90

出版年

0.76

 étrangère

0.75

Personendaten

0.74

 noqa

0.70

 uſed

0.68

 fevere

0.68

 pleaſure

0.68

hyrchwyd

0.65

 myſelf

0.65

Activations Density 0.200%

proper nouns, specifically related to places and names

No Comments

No Known Activations