INDEX

Explanations

occurrences of the name "Andrew."

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

CppMethod

-0.68

 EventEmitter

-0.67

 AssemblyTitle

-0.66

 snippetHide

-0.64

+:+

-0.64

DispatchToProps

-0.61

WaitGroup

-0.59

 propOrder

-0.56

 joaat

-0.55

BeginInit

-0.54

POSITIVE LOGITS

Điều

0.54

cuits

0.53

 Common

0.52

Zeneca

0.52

 Warhol

0.51

Через

0.50

mitsub

0.50

licata

0.49

nictví

0.48

dif

0.48

Activations Density 0.096%

occurrences of the name "Andrew."

No Comments

No Known Activations