INDEX

Explanations

lines or sections in the document that contain significant visual or formatting elements

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

Followed by underscores

np_acts-logits-general · gemini-2.0-flash

dates with times

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

出版年

-0.76

Personensuche

-0.75

/>";

-0.70

featureID

-0.69

 الحره

-0.68

 AssemblyProduct

-0.67

MigrationBuilder

-0.64

 Wikimedijinoj

-0.64

InSection

-0.62

 tartalomajánló

-0.61

POSITIVE LOGITS

________________

1.09

__

0.96

___

0.80

______

0.78

____

0.77

_______

0.76

_____

0.76

_______________

0.73

________

0.72

__________

0.72

Activations Density 0.114%

lines or sections in the document that contain significant visual or formatting elements

Followed by underscores

dates with times

No Comments

No Known Activations