INDEX

Explanations

references to historical injustices and moral criticisms related to race and political correctness

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

AnchorStyles

-0.52

 gynhyrchwyd

-0.46

TabStop

-0.44

 myſelf

-0.44

SequentialGroup

-0.43

Insee

-0.43

endphp

-0.42

autique

-0.42

 ſta

-0.42

 ComVisible

-0.41

POSITIVE LOGITS

 needlessly

0.46

relativeTime

0.40

 watermelon

0.39

 conspicuously

0.38

 mistakenly

0.37

 unnecessarily

0.36

IBAction

0.36

 supposedly

0.35

 harmless

0.35

СР

0.35

Activations Density 0.166%

references to historical injustices and moral criticisms related to race and political correctness

No Comments

No Known Activations