INDEX

Explanations

elements of structure or formatting in written content

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

</em>

-0.95

"/></

-0.62

<eos>

-0.62

Nhưng

-0.49

LikeLike

-0.49

حيان

-0.48

 мәкалә

-0.48

Và

-0.47

}}/>

-0.47

""".

-0.46

POSITIVE LOGITS

 الحره

0.73

 Roskov

0.71

 Baillargeon

0.70

twimg

0.67

SuppressMessage

0.66

SequentialGroup

0.65

XmlAccessorType

0.64

MemoryWarning

0.63

 Saltar

0.63

 kasarigan

0.63

Activations Density 0.408%

elements of structure or formatting in written content

No Comments

No Known Activations