INDEX

Explanations

elements related to customization and individualized approaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

NullCheck

-0.53

)))))

-0.49

HttpDelete

-0.49

MemoryWarning

-0.48

)])

-0.48

δει

-0.47

)))));

-0.47

towany

-0.47

iprot

-0.46

POSITIVE LOGITS

AddTagHelper

0.69

 resourceCulture

0.69

ValueStyle

0.64

 يتيمه

0.64

ViewFeatures

0.59

 lucru

0.58

 PyTuple

0.58

parsedMessage

0.58

 tfsi

0.56

 cherchés

0.56

Activations Density 0.516%

elements related to customization and individualized approaches

No Comments

No Known Activations