INDEX

Explanations

assertions and conclusions made by the author or speaker

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

Sentences starting with "We [verb]"

np_acts-logits-general · gemini-2.0-flash

"we" followed by belief or 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

存于互联网档案馆

-0.85

StructEnd

-0.65

AddTagHelper

-0.62

StoreMessageInfo

-0.60

oplasmic

-0.59

RTEE

-0.59

ThroughAttribute

-0.58

ISupport

-0.57

 Potosí

-0.56

 lizenz

-0.54

POSITIVE LOGITS

 shall

0.67

IsPostBack

0.53

too

0.50

 Shall

0.50

BeginInit

0.49

المشاركات

0.48

 SHALL

0.48

 cannot

0.47

 Fußballspieler

0.47

 propOrder

0.46

Activations Density 0.294%

assertions and conclusions made by the author or speaker

Sentences starting with "We [verb]"

"we" followed by belief or conclusion

No Comments

No Known Activations