INDEX

Explanations

resources related to Native American history and culture

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

"Has" followed by positive information/resources

np_acts-logits-general · gemini-2.0-flash

useful resources and information

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

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

RegressionTest

-0.99

GEBURTS

-0.87

tanleria

-0.83

ContentAsync

-0.82

thâu

-0.79

TagMode

-0.76

ModelAdmin

-0.75

ConstraintMaker

-0.75

awtextra

-0.73

 NSCoder

-0.73

POSITIVE LOGITS

 resources

1.18

 helpful

1.16

 useful

1.11

 information

1.01

 resource

1.00

 links

0.99

Useful

0.94

 downloadable

0.94

useful

0.94

Resources

0.92

Activations Density 0.367%

resources related to Native American history and culture

"Has" followed by positive information/resources

useful resources and information

No Comments

No Known Activations