INDEX

Explanations

geographic locations and their associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 puissiez

-0.61

 архивлан

-0.60

 necesite

-0.60

dération

-0.59

 antemano

-0.58

ipient

-0.55

kinci

-0.55

InvalidProtocol

-0.54

 photolibrary

-0.54

elry

-0.53

POSITIVE LOGITS

ViewFeatures

0.72

XtraReports

0.67

 PyQt

0.61

 DevExpress

0.59

writerow

0.56

 reasons

0.56

 ApiException

0.56

 препратки

0.56

kuuta

0.53

 verw

0.53

Activations Density 0.797%

geographic locations and their associated entities

No Comments

No Known Activations