INDEX

Explanations

phrases related to public events and community engagement

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

出版年

-0.70

 Roskov

-0.68

OGND

-0.66

 ModelExpression

-0.66

 препратки

-0.65

EndInit

-0.65

 venons

-0.64

 StringTokenizer

-0.63

ReusableCell

-0.63

newswire

-0.63

POSITIVE LOGITS

 starting

0.83

 Starting

0.73

Starting

0.67

 beginning

0.67

starting

0.64

at

0.62

STARTING

0.60

 STARTING

0.56

 noon

0.54

 will

0.52

Activations Density 0.082%

phrases related to public events and community engagement

No Comments

No Known Activations