INDEX

Explanations

references to geographic locations, specifically cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

providedIn

-0.73

Vidite

-0.69

 المعرف

-0.64

 AssemblyTitle

-0.63

 disponibilités

-0.60

oredCriteria

-0.58

arcoma

-0.57

MessageTagHelper

-0.54

hasMoreElements

-0.53

//

-0.52

POSITIVE LOGITS

 initComponents

0.72

 suburb

0.63

 headquartered

0.63

 metropolitan

0.61

derry

0.60

 capitale

0.60

 suburbs

0.60

ienne

0.60

 Metropolitan

0.58

 skyline

0.57

Activations Density 0.313%

references to geographic locations, specifically cities

No Comments

No Known Activations