INDEX

Explanations

marks indicating conclusions or summarizing remarks in a document

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

Tokens preceding ordinal indicators

np_acts-logits-general · gemini-2.0-flash

And followed by conclusion

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

 kasarigan

-0.75

+:+

-0.64

landers

-0.63

 дописавши

-0.62

 disambiguazione

-0.61

rdoba

-0.57

ponses

-0.56

featureID

-0.56

ContentAsync

-0.56

openzeppelin

-0.55

POSITIVE LOGITS

 finally

3.82

 Finally

3.67

Finally

3.59

finally

3.40

 lastly

3.30

 Lastly

3.17

Lastly

3.15

 enfin

3.13

 finalmente

2.87

 Enfin

2.86

Activations Density 0.766%

marks indicating conclusions or summarizing remarks in a document

Tokens preceding ordinal indicators

And followed by conclusion

No Comments

No Known Activations