INDEX

Explanations

terms related to negligence and moral culpability

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

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

-0.86

IsContent

-0.83

ViewFeatures

-0.75

jspb

-0.73

TypedDataSet

-0.69

XmlAccessorType

-0.67

:✨

-0.67

Aholisi

-0.65

 ThemeData

-0.64

AndEndTag

-0.63

POSITIVE LOGITS

ness

0.83

انه

0.79

neſs

0.71

est

0.69

 effort

0.65

nesses

0.64

NESS

0.63

 cref

0.61

 démarche

0.60

 souls

0.58

Activations Density 0.302%

terms related to negligence and moral culpability

No Comments

No Known Activations